--- _id: '1098' abstract: - lang: eng text: Better understanding of the potential benefits of information transfer and representation learning is an important step towards the goal of building intelligent systems that are able to persist in the world and learn over time. In this work, we consider a setting where the learner encounters a stream of tasks but is able to retain only limited information from each encountered task, such as a learned predictor. In contrast to most previous works analyzing this scenario, we do not make any distributional assumptions on the task generating process. Instead, we formulate a complexity measure that captures the diversity of the observed tasks. We provide a lifelong learning algorithm with error guarantees for every observed task (rather than on average). We show sample complexity reductions in comparison to solving every task in isolation in terms of our task complexity measure. Further, our algorithmic framework can naturally be viewed as learning a representation from encountered tasks with a neural network. acknowledgement: "This work was in parts funded by the European Research Council under the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement no 308036.\r\n\r\n" alternative_title: - Advances in Neural Information Processing Systems author: - first_name: Anastasia full_name: Pentina, Anastasia id: 42E87FC6-F248-11E8-B48F-1D18A9856A87 last_name: Pentina - first_name: Ruth full_name: Urner, Ruth last_name: Urner citation: ama: 'Pentina A, Urner R. Lifelong learning with weighted majority votes. In: Vol 29. Neural Information Processing Systems; 2016:3619-3627.' apa: 'Pentina, A., & Urner, R. (2016). Lifelong learning with weighted majority votes (Vol. 29, pp. 3619–3627). Presented at the NIPS: Neural Information Processing Systems, Barcelona, Spain: Neural Information Processing Systems.' chicago: Pentina, Anastasia, and Ruth Urner. “Lifelong Learning with Weighted Majority Votes,” 29:3619–27. Neural Information Processing Systems, 2016. ieee: 'A. Pentina and R. Urner, “Lifelong learning with weighted majority votes,” presented at the NIPS: Neural Information Processing Systems, Barcelona, Spain, 2016, vol. 29, pp. 3619–3627.' ista: 'Pentina A, Urner R. 2016. Lifelong learning with weighted majority votes. NIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 29, 3619–3627.' mla: Pentina, Anastasia, and Ruth Urner. Lifelong Learning with Weighted Majority Votes. Vol. 29, Neural Information Processing Systems, 2016, pp. 3619–27. short: A. Pentina, R. Urner, in:, Neural Information Processing Systems, 2016, pp. 3619–3627. conference: end_date: 2016-12-10 location: Barcelona, Spain name: 'NIPS: Neural Information Processing Systems' start_date: 2016-12-05 date_created: 2018-12-11T11:50:08Z date_published: 2016-12-01T00:00:00Z date_updated: 2021-01-12T06:48:15Z day: '01' ddc: - '006' department: - _id: ChLa ec_funded: 1 file: - access_level: open_access content_type: application/pdf creator: system date_created: 2018-12-12T10:12:42Z date_updated: 2018-12-12T10:12:42Z file_id: '4961' file_name: IST-2017-775-v1+1_main.pdf file_size: 237111 relation: main_file - access_level: open_access content_type: application/pdf creator: system date_created: 2018-12-12T10:12:43Z date_updated: 2018-12-12T10:12:43Z file_id: '4962' file_name: IST-2017-775-v1+2_supplementary.pdf file_size: 185818 relation: main_file file_date_updated: 2018-12-12T10:12:43Z has_accepted_license: '1' intvolume: ' 29' language: - iso: eng month: '12' oa: 1 oa_version: Published Version page: 3619-3627 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication_status: published publisher: Neural Information Processing Systems publist_id: '6277' pubrep_id: '775' quality_controlled: '1' scopus_import: 1 status: public title: Lifelong learning with weighted majority votes type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 volume: 29 year: '2016' ... --- _id: '1102' abstract: - lang: eng text: Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount of model-specific additional annotation. The main idea is to cluster a deep network\'s mid-level representations and assign object or distractor labels to each cluster. Experiments show substantially improved localization results on the challenging ILSVC2014 dataset for bounding box detection and the PASCAL VOC2012 dataset for semantic segmentation. acknowledgement: "This work was funded in parts by the European Research Council\r\nunder the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant\r\nagreement no 308036. We gratefully acknowledge the support of NVIDIA Corporation with\r\nthe donation of the GPUs used for this research." author: - first_name: Alexander full_name: Kolesnikov, Alexander id: 2D157DB6-F248-11E8-B48F-1D18A9856A87 last_name: Kolesnikov - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Kolesnikov A, Lampert C. Improving weakly-supervised object localization by micro-annotation. In: Proceedings of the British Machine Vision Conference 2016. Vol 2016-September. BMVA Press; 2016:92.1-92.12. doi:10.5244/C.30.92' apa: 'Kolesnikov, A., & Lampert, C. (2016). Improving weakly-supervised object localization by micro-annotation. In Proceedings of the British Machine Vision Conference 2016 (Vol. 2016–September, p. 92.1-92.12). York, United Kingdom: BMVA Press. https://doi.org/10.5244/C.30.92' chicago: Kolesnikov, Alexander, and Christoph Lampert. “Improving Weakly-Supervised Object Localization by Micro-Annotation.” In Proceedings of the British Machine Vision Conference 2016, 2016–September:92.1-92.12. BMVA Press, 2016. https://doi.org/10.5244/C.30.92. ieee: A. Kolesnikov and C. Lampert, “Improving weakly-supervised object localization by micro-annotation,” in Proceedings of the British Machine Vision Conference 2016, York, United Kingdom, 2016, vol. 2016–September, p. 92.1-92.12. ista: 'Kolesnikov A, Lampert C. 2016. Improving weakly-supervised object localization by micro-annotation. Proceedings of the British Machine Vision Conference 2016. BMVC: British Machine Vision Conference vol. 2016–September, 92.1-92.12.' mla: Kolesnikov, Alexander, and Christoph Lampert. “Improving Weakly-Supervised Object Localization by Micro-Annotation.” Proceedings of the British Machine Vision Conference 2016, vol. 2016–September, BMVA Press, 2016, p. 92.1-92.12, doi:10.5244/C.30.92. short: A. Kolesnikov, C. Lampert, in:, Proceedings of the British Machine Vision Conference 2016, BMVA Press, 2016, p. 92.1-92.12. conference: end_date: 2016-09-22 location: York, United Kingdom name: 'BMVC: British Machine Vision Conference' start_date: 2016-09-19 date_created: 2018-12-11T11:50:09Z date_published: 2016-09-01T00:00:00Z date_updated: 2021-01-12T06:48:18Z day: '01' department: - _id: ChLa doi: 10.5244/C.30.92 ec_funded: 1 language: - iso: eng main_file_link: - open_access: '1' url: http://www.bmva.org/bmvc/2016/papers/paper092/paper092.pdf month: '09' oa: 1 oa_version: Published Version page: 92.1-92.12 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication: Proceedings of the British Machine Vision Conference 2016 publication_status: published publisher: BMVA Press publist_id: '6273' quality_controlled: '1' scopus_import: 1 status: public title: Improving weakly-supervised object localization by micro-annotation type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 volume: 2016-September year: '2016' ... --- _id: '1214' abstract: - lang: eng text: 'With the accelerated development of robot technologies, optimal control becomes one of the central themes of research. In traditional approaches, the controller, by its internal functionality, finds appropriate actions on the basis of the history of sensor values, guided by the goals, intentions, objectives, learning schemes, and so forth. While very successful with classical robots, these methods run into severe difficulties when applied to soft robots, a new field of robotics with large interest for human-robot interaction. We claim that a novel controller paradigm opens new perspective for this field. This paper applies a recently developed neuro controller with differential extrinsic synaptic plasticity to a muscle-tendon driven arm-shoulder system from the Myorobotics toolkit. In the experiments, we observe a vast variety of self-organized behavior patterns: when left alone, the arm realizes pseudo-random sequences of different poses. By applying physical forces, the system can be entrained into definite motion patterns like wiping a table. Most interestingly, after attaching an object, the controller gets in a functional resonance with the object''s internal dynamics, starting to shake spontaneously bottles half-filled with water or sensitively driving an attached pendulum into a circular mode. When attached to the crank of a wheel the neural system independently develops to rotate it. In this way, the robot discovers affordances of objects its body is interacting with.' acknowledgement: RD thanks for the hospitality at the Max-Planck-Institute and for helpful discussions with Nihat Ay and Keyan Zahedi. article_number: '7759138' author: - first_name: Georg S full_name: Martius, Georg S id: 3A276B68-F248-11E8-B48F-1D18A9856A87 last_name: Martius - first_name: Raphael full_name: Hostettler, Raphael last_name: Hostettler - first_name: Alois full_name: Knoll, Alois last_name: Knoll - first_name: Ralf full_name: Der, Ralf last_name: Der citation: ama: 'Martius GS, Hostettler R, Knoll A, Der R. Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm. In: Vol 2016-November. IEEE; 2016. doi:10.1109/IROS.2016.7759138' apa: 'Martius, G. S., Hostettler, R., Knoll, A., & Der, R. (2016). Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm (Vol. 2016–November). Presented at the IEEE RSJ International Conference on Intelligent Robots and Systems IROS , Daejeon, Korea: IEEE. https://doi.org/10.1109/IROS.2016.7759138' chicago: 'Martius, Georg S, Raphael Hostettler, Alois Knoll, and Ralf Der. “Compliant Control for Soft Robots: Emergent Behavior of a Tendon Driven Anthropomorphic Arm,” Vol. 2016–November. IEEE, 2016. https://doi.org/10.1109/IROS.2016.7759138.' ieee: 'G. S. Martius, R. Hostettler, A. Knoll, and R. Der, “Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm,” presented at the IEEE RSJ International Conference on Intelligent Robots and Systems IROS , Daejeon, Korea, 2016, vol. 2016–November.' ista: 'Martius GS, Hostettler R, Knoll A, Der R. 2016. Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm. IEEE RSJ International Conference on Intelligent Robots and Systems IROS vol. 2016–November, 7759138.' mla: 'Martius, Georg S., et al. Compliant Control for Soft Robots: Emergent Behavior of a Tendon Driven Anthropomorphic Arm. Vol. 2016–November, 7759138, IEEE, 2016, doi:10.1109/IROS.2016.7759138.' short: G.S. Martius, R. Hostettler, A. Knoll, R. Der, in:, IEEE, 2016. conference: end_date: 2016-09-14 location: Daejeon, Korea name: 'IEEE RSJ International Conference on Intelligent Robots and Systems IROS ' start_date: 2016-09-09 date_created: 2018-12-11T11:50:45Z date_published: 2016-11-28T00:00:00Z date_updated: 2021-01-12T06:49:08Z day: '28' department: - _id: ChLa - _id: GaTk doi: 10.1109/IROS.2016.7759138 language: - iso: eng month: '11' oa_version: None publication_status: published publisher: IEEE publist_id: '6121' quality_controlled: '1' scopus_import: 1 status: public title: 'Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm' type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 volume: 2016-November year: '2016' ... --- _id: '1369' abstract: - lang: eng text: 'We introduce a new loss function for the weakly-supervised training of semantic image segmentation models based on three guiding principles: to seed with weak localization cues, to expand objects based on the information about which classes can occur in an image, and to constrain the segmentations to coincide with object boundaries. We show experimentally that training a deep convolutional neural network using the proposed loss function leads to substantially better segmentations than previous state-of-the-art methods on the challenging PASCAL VOC 2012 dataset. We furthermore give insight into the working mechanism of our method by a detailed experimental study that illustrates how the segmentation quality is affected by each term of the proposed loss function as well as their combinations.' alternative_title: - LNCS author: - first_name: Alexander full_name: Kolesnikov, Alexander id: 2D157DB6-F248-11E8-B48F-1D18A9856A87 last_name: Kolesnikov - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Kolesnikov A, Lampert C. Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In: Vol 9908. Springer; 2016:695-711. doi:10.1007/978-3-319-46493-0_42' apa: 'Kolesnikov, A., & Lampert, C. (2016). Seed, expand and constrain: Three principles for weakly-supervised image segmentation (Vol. 9908, pp. 695–711). Presented at the ECCV: European Conference on Computer Vision, Amsterdam, The Netherlands: Springer. https://doi.org/10.1007/978-3-319-46493-0_42' chicago: 'Kolesnikov, Alexander, and Christoph Lampert. “Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation,” 9908:695–711. Springer, 2016. https://doi.org/10.1007/978-3-319-46493-0_42.' ieee: 'A. Kolesnikov and C. Lampert, “Seed, expand and constrain: Three principles for weakly-supervised image segmentation,” presented at the ECCV: European Conference on Computer Vision, Amsterdam, The Netherlands, 2016, vol. 9908, pp. 695–711.' ista: 'Kolesnikov A, Lampert C. 2016. Seed, expand and constrain: Three principles for weakly-supervised image segmentation. ECCV: European Conference on Computer Vision, LNCS, vol. 9908, 695–711.' mla: 'Kolesnikov, Alexander, and Christoph Lampert. Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation. Vol. 9908, Springer, 2016, pp. 695–711, doi:10.1007/978-3-319-46493-0_42.' short: A. Kolesnikov, C. Lampert, in:, Springer, 2016, pp. 695–711. conference: end_date: 2016-10-14 location: Amsterdam, The Netherlands name: 'ECCV: European Conference on Computer Vision' start_date: 2016-10-11 date_created: 2018-12-11T11:51:37Z date_published: 2016-09-15T00:00:00Z date_updated: 2021-01-12T06:50:12Z day: '15' department: - _id: ChLa doi: 10.1007/978-3-319-46493-0_42 ec_funded: 1 intvolume: ' 9908' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/1603.06098 month: '09' oa: 1 oa_version: Preprint page: 695 - 711 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication_status: published publisher: Springer publist_id: '5842' quality_controlled: '1' scopus_import: 1 status: public title: 'Seed, expand and constrain: Three principles for weakly-supervised image segmentation' type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 volume: 9908 year: '2016' ... --- _id: '1707' abstract: - lang: eng text: "Volunteer supporters play an important role in modern crisis and disaster management. In the times of mobile Internet devices, help from thousands of volunteers can be requested within a short time span, thus relieving professional helpers from minor chores or geographically spread-out tasks. However, the simultaneous availability of many volunteers also poses new problems. In particular, the volunteer efforts must be well coordinated, or otherwise situations might emerge in which too many idle volunteers at one location become more of a burden than a relief to the professionals.\r\nIn this work, we study the task of optimally assigning volunteers to selected locations, e.g. in order to perform regular measurements, to report on damage, or to distribute information or resources to the population in a crisis situation. We formulate the assignment tasks as an optimization problem and propose an effective and efficient solution procedure. Experiments on real data of the Team Österreich, consisting of over 36,000 Austrian volunteers, show the effectiveness and efficiency of our approach." acknowledgement: The DRIVER FP7 project has received funding from the European Unions Seventh Framework Programme for research, technological development and demonstration under grant agreement no 607798. RE-ACTA was funded within the framework of the Austrian Security Research Programme KIRAS by the Federal Ministry for Transport, Innovation and Technology. article_number: '7402041' author: - first_name: Jasmin full_name: Pielorz, Jasmin id: 49BC895A-F248-11E8-B48F-1D18A9856A87 last_name: Pielorz - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Pielorz J, Lampert C. Optimal geospatial allocation of volunteers for crisis management. In: IEEE; 2016. doi:10.1109/ICT-DM.2015.7402041' apa: 'Pielorz, J., & Lampert, C. (2016). Optimal geospatial allocation of volunteers for crisis management. Presented at the ICT-DM: Information and Communication Technologies for Disaster Management, Rennes, France: IEEE. https://doi.org/10.1109/ICT-DM.2015.7402041' chicago: Pielorz, Jasmin, and Christoph Lampert. “Optimal Geospatial Allocation of Volunteers for Crisis Management.” IEEE, 2016. https://doi.org/10.1109/ICT-DM.2015.7402041. ieee: 'J. Pielorz and C. Lampert, “Optimal geospatial allocation of volunteers for crisis management,” presented at the ICT-DM: Information and Communication Technologies for Disaster Management, Rennes, France, 2016.' ista: 'Pielorz J, Lampert C. 2016. Optimal geospatial allocation of volunteers for crisis management. ICT-DM: Information and Communication Technologies for Disaster Management, 7402041.' mla: Pielorz, Jasmin, and Christoph Lampert. Optimal Geospatial Allocation of Volunteers for Crisis Management. 7402041, IEEE, 2016, doi:10.1109/ICT-DM.2015.7402041. short: J. Pielorz, C. Lampert, in:, IEEE, 2016. conference: end_date: 2015-12-02 location: Rennes, France name: 'ICT-DM: Information and Communication Technologies for Disaster Management' start_date: 2015-11-30 date_created: 2018-12-11T11:53:35Z date_published: 2016-02-11T00:00:00Z date_updated: 2021-01-12T06:52:39Z day: '11' department: - _id: ChLa doi: 10.1109/ICT-DM.2015.7402041 language: - iso: eng month: '02' oa_version: None publication_status: published publisher: IEEE publist_id: '5429' quality_controlled: '1' scopus_import: 1 status: public title: Optimal geospatial allocation of volunteers for crisis management type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 year: '2016' ... --- _id: '8094' abstract: - lang: eng text: 'With the accelerated development of robot technologies, optimal control becomes one of the central themes of research. In traditional approaches, the controller, by its internal functionality, finds appropriate actions on the basis of the history of sensor values, guided by the goals, intentions, objectives, learning schemes, and so forth. The idea is that the controller controls the world---the body plus its environment---as reliably as possible. This paper focuses on new lines of self-organization for developmental robotics. We apply the recently developed differential extrinsic synaptic plasticity to a muscle-tendon driven arm-shoulder system from the Myorobotics toolkit. In the experiments, we observe a vast variety of self-organized behavior patterns: when left alone, the arm realizes pseudo-random sequences of different poses. By applying physical forces, the system can be entrained into definite motion patterns like wiping a table. Most interestingly, after attaching an object, the controller gets in a functional resonance with the object''s internal dynamics, starting to shake spontaneously bottles half-filled with water or sensitively driving an attached pendulum into a circular mode. When attached to the crank of a wheel the neural system independently discovers how to rotate it. In this way, the robot discovers affordances of objects its body is interacting with.' article_processing_charge: No author: - first_name: Georg S full_name: Martius, Georg S id: 3A276B68-F248-11E8-B48F-1D18A9856A87 last_name: Martius - first_name: Rafael full_name: Hostettler, Rafael last_name: Hostettler - first_name: Alois full_name: Knoll, Alois last_name: Knoll - first_name: Ralf full_name: Der, Ralf last_name: Der citation: ama: 'Martius GS, Hostettler R, Knoll A, Der R. Self-organized control of an tendon driven arm by differential extrinsic plasticity. In: Proceedings of the Artificial Life Conference 2016. Vol 28. MIT Press; 2016:142-143. doi:10.7551/978-0-262-33936-0-ch029' apa: 'Martius, G. S., Hostettler, R., Knoll, A., & Der, R. (2016). Self-organized control of an tendon driven arm by differential extrinsic plasticity. In Proceedings of the Artificial Life Conference 2016 (Vol. 28, pp. 142–143). Cancun, Mexico: MIT Press. https://doi.org/10.7551/978-0-262-33936-0-ch029' chicago: Martius, Georg S, Rafael Hostettler, Alois Knoll, and Ralf Der. “Self-Organized Control of an Tendon Driven Arm by Differential Extrinsic Plasticity.” In Proceedings of the Artificial Life Conference 2016, 28:142–43. MIT Press, 2016. https://doi.org/10.7551/978-0-262-33936-0-ch029. ieee: G. S. Martius, R. Hostettler, A. Knoll, and R. Der, “Self-organized control of an tendon driven arm by differential extrinsic plasticity,” in Proceedings of the Artificial Life Conference 2016, Cancun, Mexico, 2016, vol. 28, pp. 142–143. ista: 'Martius GS, Hostettler R, Knoll A, Der R. 2016. Self-organized control of an tendon driven arm by differential extrinsic plasticity. Proceedings of the Artificial Life Conference 2016. ALIFE 2016: 15th International Conference on the Synthesis and Simulation of Living Systems vol. 28, 142–143.' mla: Martius, Georg S., et al. “Self-Organized Control of an Tendon Driven Arm by Differential Extrinsic Plasticity.” Proceedings of the Artificial Life Conference 2016, vol. 28, MIT Press, 2016, pp. 142–43, doi:10.7551/978-0-262-33936-0-ch029. short: G.S. Martius, R. Hostettler, A. Knoll, R. Der, in:, Proceedings of the Artificial Life Conference 2016, MIT Press, 2016, pp. 142–143. conference: end_date: 2016-07-08 location: Cancun, Mexico name: 'ALIFE 2016: 15th International Conference on the Synthesis and Simulation of Living Systems' start_date: 2016-07-04 date_created: 2020-07-05T22:00:47Z date_published: 2016-09-01T00:00:00Z date_updated: 2021-01-12T08:16:53Z day: '01' ddc: - '610' department: - _id: ChLa - _id: GaTk doi: 10.7551/978-0-262-33936-0-ch029 ec_funded: 1 file: - access_level: open_access checksum: cff63e7a4b8ac466ba51a9c84153a940 content_type: application/pdf creator: cziletti date_created: 2020-07-06T12:59:09Z date_updated: 2020-07-14T12:48:09Z file_id: '8096' file_name: 2016_ProcALIFE_Martius.pdf file_size: 678670 relation: main_file file_date_updated: 2020-07-14T12:48:09Z has_accepted_license: '1' intvolume: ' 28' language: - iso: eng month: '09' oa: 1 oa_version: Published Version page: 142-143 project: - _id: 25681D80-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '291734' name: International IST Postdoc Fellowship Programme publication: Proceedings of the Artificial Life Conference 2016 publication_identifier: isbn: - '9780262339360' publication_status: published publisher: MIT Press quality_controlled: '1' scopus_import: 1 status: public title: Self-organized control of an tendon driven arm by differential extrinsic plasticity tmp: image: /images/cc_by.png legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0) short: CC BY (4.0) type: conference user_id: D865714E-FA4E-11E9-B85B-F5C5E5697425 volume: 28 year: '2016' ... --- _id: '1126' abstract: - lang: eng text: "Traditionally machine learning has been focusing on the problem of solving a single\r\ntask in isolation. While being quite well understood, this approach disregards an\r\nimportant aspect of human learning: when facing a new problem, humans are able to\r\nexploit knowledge acquired from previously learned tasks. Intuitively, access to several\r\nproblems simultaneously or sequentially could also be advantageous for a machine\r\nlearning system, especially if these tasks are closely related. Indeed, results of many\r\nempirical studies have provided justification for this intuition. However, theoretical\r\njustifications of this idea are rather limited.\r\nThe focus of this thesis is to expand the understanding of potential benefits of information\r\ntransfer between several related learning problems. We provide theoretical\r\nanalysis for three scenarios of multi-task learning - multiple kernel learning, sequential\r\nlearning and active task selection. We also provide a PAC-Bayesian perspective on\r\nlifelong learning and investigate how the task generation process influences the generalization\r\nguarantees in this scenario. In addition, we show how some of the obtained\r\ntheoretical results can be used to derive principled multi-task and lifelong learning\r\nalgorithms and illustrate their performance on various synthetic and real-world datasets." acknowledgement: "First and foremost I would like to express my gratitude to my supervisor, Christoph\r\nLampert. Thank you for your patience in teaching me all aspects of doing research\r\n(including English grammar), for your trust in my capabilities and endless support. Thank\r\nyou for granting me freedom in my research and, at the same time, having time and\r\nhelping me cope with the consequences whenever I needed it. Thank you for creating\r\nan excellent atmosphere in the group, it was a great pleasure and honor to be a part of\r\nit. There could not have been a better and more inspiring adviser and mentor.\r\nI thank Shai Ben-David for welcoming me into his group at the University of Waterloo,\r\nfor inspiring discussions and support. It was a great pleasure to work together. I am\r\nalso thankful to Ruth Urner for hosting me at the Max-Planck Institute Tübingen, for the\r\nfruitful collaboration and for taking care of me during that not-so-sunny month of May.\r\nI thank Jan Maas for kindly joining my thesis committee despite the short notice and\r\nproviding me with insightful comments.\r\nI would like to thank my colleagues for their support, entertaining conversations and\r\nendless table soccer games we shared together: Georg, Jan, Amelie and Emilie, Michal\r\nand Alex, Alex K. and Alex Z., Thomas, Sameh, Vlad, Mayu, Nathaniel, Silvester, Neel,\r\nCsaba, Vladimir, Morten. Thank you, Mabel and Ram, for the wonderful time we spent\r\ntogether. I am thankful to Shrinu and Samira for taking care of me during my stay at the\r\nUniversity of Waterloo. Special thanks to Viktoriia for her never-ending optimism and for\r\nbeing so inspiring and supportive, especially at the beginning of my PhD journey.\r\nThanks to IST administration, in particular, Vlad and Elisabeth for shielding me from\r\nmost of the bureaucratic paperwork.\r\n\r\nThis dissertation would not have been possible without funding from the European\r\nResearch Council under the European Union's Seventh Framework Programme\r\n(FP7/2007-2013)/ERC grant agreement no 308036." alternative_title: - ISTA Thesis article_processing_charge: No author: - first_name: Anastasia full_name: Pentina, Anastasia id: 42E87FC6-F248-11E8-B48F-1D18A9856A87 last_name: Pentina citation: ama: Pentina A. Theoretical foundations of multi-task lifelong learning. 2016. doi:10.15479/AT:ISTA:TH_776 apa: Pentina, A. (2016). Theoretical foundations of multi-task lifelong learning. Institute of Science and Technology Austria. https://doi.org/10.15479/AT:ISTA:TH_776 chicago: Pentina, Anastasia. “Theoretical Foundations of Multi-Task Lifelong Learning.” Institute of Science and Technology Austria, 2016. https://doi.org/10.15479/AT:ISTA:TH_776. ieee: A. Pentina, “Theoretical foundations of multi-task lifelong learning,” Institute of Science and Technology Austria, 2016. ista: Pentina A. 2016. Theoretical foundations of multi-task lifelong learning. Institute of Science and Technology Austria. mla: Pentina, Anastasia. Theoretical Foundations of Multi-Task Lifelong Learning. Institute of Science and Technology Austria, 2016, doi:10.15479/AT:ISTA:TH_776. short: A. Pentina, Theoretical Foundations of Multi-Task Lifelong Learning, Institute of Science and Technology Austria, 2016. date_created: 2018-12-11T11:50:17Z date_published: 2016-11-01T00:00:00Z date_updated: 2023-09-07T11:52:03Z day: '01' ddc: - '006' degree_awarded: PhD department: - _id: ChLa doi: 10.15479/AT:ISTA:TH_776 ec_funded: 1 file: - access_level: open_access content_type: application/pdf creator: system date_created: 2018-12-12T10:14:07Z date_updated: 2018-12-12T10:14:07Z file_id: '5056' file_name: IST-2017-776-v1+1_Pentina_Thesis_2016.pdf file_size: 2140062 relation: main_file file_date_updated: 2018-12-12T10:14:07Z has_accepted_license: '1' language: - iso: eng month: '11' oa: 1 oa_version: Published Version page: '127' project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication_identifier: issn: - 2663-337X publication_status: published publisher: Institute of Science and Technology Austria publist_id: '6234' pubrep_id: '776' status: public supervisor: - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 title: Theoretical foundations of multi-task lifelong learning type: dissertation user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 year: '2016' ... --- _id: '1425' abstract: - lang: eng text: 'In this work we aim at extending the theoretical foundations of lifelong learning. Previous work analyzing this scenario is based on the assumption that learning tasks are sampled i.i.d. from a task environment or limited to strongly constrained data distributions. Instead, we study two scenarios when lifelong learning is possible, even though the observed tasks do not form an i.i.d. sample: first, when they are sampled from the same environment, but possibly with dependencies, and second, when the task environment is allowed to change over time in a consistent way. In the first case we prove a PAC-Bayesian theorem that can be seen as a direct generalization of the analogous previous result for the i.i.d. case. For the second scenario we propose to learn an inductive bias in form of a transfer procedure. We present a generalization bound and show on a toy example how it can be used to identify a beneficial transfer algorithm.' alternative_title: - Advances in Neural Information Processing Systems author: - first_name: Anastasia full_name: Pentina, Anastasia id: 42E87FC6-F248-11E8-B48F-1D18A9856A87 last_name: Pentina - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Pentina A, Lampert C. Lifelong learning with non-i.i.d. tasks. In: Vol 2015. Neural Information Processing Systems; 2015:1540-1548.' apa: 'Pentina, A., & Lampert, C. (2015). Lifelong learning with non-i.i.d. tasks (Vol. 2015, pp. 1540–1548). Presented at the NIPS: Neural Information Processing Systems, Montreal, Canada: Neural Information Processing Systems.' chicago: Pentina, Anastasia, and Christoph Lampert. “Lifelong Learning with Non-i.i.d. Tasks,” 2015:1540–48. Neural Information Processing Systems, 2015. ieee: 'A. Pentina and C. Lampert, “Lifelong learning with non-i.i.d. tasks,” presented at the NIPS: Neural Information Processing Systems, Montreal, Canada, 2015, vol. 2015, pp. 1540–1548.' ista: 'Pentina A, Lampert C. 2015. Lifelong learning with non-i.i.d. tasks. NIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 2015, 1540–1548.' mla: Pentina, Anastasia, and Christoph Lampert. Lifelong Learning with Non-i.i.d. Tasks. Vol. 2015, Neural Information Processing Systems, 2015, pp. 1540–48. short: A. Pentina, C. Lampert, in:, Neural Information Processing Systems, 2015, pp. 1540–1548. conference: end_date: 2015-12-12 location: Montreal, Canada name: 'NIPS: Neural Information Processing Systems' start_date: 2015-12-07 date_created: 2018-12-11T11:51:57Z date_published: 2015-01-01T00:00:00Z date_updated: 2021-01-12T06:50:39Z day: '01' department: - _id: ChLa ec_funded: 1 intvolume: ' 2015' language: - iso: eng main_file_link: - open_access: '1' url: http://papers.nips.cc/paper/6007-lifelong-learning-with-non-iid-tasks month: '01' oa: 1 oa_version: None page: 1540 - 1548 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication_status: published publisher: Neural Information Processing Systems publist_id: '5781' quality_controlled: '1' scopus_import: 1 status: public title: Lifelong learning with non-i.i.d. tasks type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 volume: 2015 year: '2015' ... --- _id: '1533' abstract: - lang: eng text: This paper addresses the problem of semantic segmentation, where the possible class labels are from a predefined set. We exploit top-down guidance, i.e., the coarse localization of the objects and their class labels provided by object detectors. For each detected bounding box, figure-ground segmentation is performed and the final result is achieved by merging the figure-ground segmentations. The main idea of the proposed approach, which is presented in our preliminary work, is to reformulate the figure-ground segmentation problem as sparse reconstruction pursuing the object mask in a nonparametric manner. The latent segmentation mask should be coherent subject to sparse error caused by intra-category diversity; thus, the object mask is inferred by making use of sparse representations over the training set. To handle local spatial deformations, local patch-level masks are also considered and inferred by sparse representations over the spatially nearby patches. The sparse reconstruction coefficients and the latent mask are alternately optimized by applying the Lasso algorithm and the accelerated proximal gradient method. The proposed formulation results in a convex optimization problem; thus, the global optimal solution is achieved. In this paper, we provide theoretical analysis of the convergence and optimality. We also give an extended numerical analysis of the proposed algorithm and a comprehensive comparison with the related semantic segmentation methods on the challenging PASCAL visual object class object segmentation datasets and the Weizmann horse dataset. The experimental results demonstrate that the proposed algorithm achieves a competitive performance when compared with the state of the arts. author: - first_name: Wei full_name: Xia, Wei last_name: Xia - first_name: Csaba full_name: Domokos, Csaba id: 492DACF8-F248-11E8-B48F-1D18A9856A87 last_name: Domokos - first_name: Junjun full_name: Xiong, Junjun last_name: Xiong - first_name: Loongfah full_name: Cheong, Loongfah last_name: Cheong - first_name: Shuicheng full_name: Yan, Shuicheng last_name: Yan citation: ama: Xia W, Domokos C, Xiong J, Cheong L, Yan S. Segmentation over detection via optimal sparse reconstructions. IEEE Transactions on Circuits and Systems for Video Technology. 2015;25(8):1295-1308. doi:10.1109/TCSVT.2014.2379972 apa: Xia, W., Domokos, C., Xiong, J., Cheong, L., & Yan, S. (2015). Segmentation over detection via optimal sparse reconstructions. IEEE Transactions on Circuits and Systems for Video Technology. IEEE. https://doi.org/10.1109/TCSVT.2014.2379972 chicago: Xia, Wei, Csaba Domokos, Junjun Xiong, Loongfah Cheong, and Shuicheng Yan. “Segmentation over Detection via Optimal Sparse Reconstructions.” IEEE Transactions on Circuits and Systems for Video Technology. IEEE, 2015. https://doi.org/10.1109/TCSVT.2014.2379972. ieee: W. Xia, C. Domokos, J. Xiong, L. Cheong, and S. Yan, “Segmentation over detection via optimal sparse reconstructions,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 8. IEEE, pp. 1295–1308, 2015. ista: Xia W, Domokos C, Xiong J, Cheong L, Yan S. 2015. Segmentation over detection via optimal sparse reconstructions. IEEE Transactions on Circuits and Systems for Video Technology. 25(8), 1295–1308. mla: Xia, Wei, et al. “Segmentation over Detection via Optimal Sparse Reconstructions.” IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 8, IEEE, 2015, pp. 1295–308, doi:10.1109/TCSVT.2014.2379972. short: W. Xia, C. Domokos, J. Xiong, L. Cheong, S. Yan, IEEE Transactions on Circuits and Systems for Video Technology 25 (2015) 1295–1308. date_created: 2018-12-11T11:52:34Z date_published: 2015-08-01T00:00:00Z date_updated: 2021-01-12T06:51:26Z day: '01' department: - _id: ChLa doi: 10.1109/TCSVT.2014.2379972 intvolume: ' 25' issue: '8' language: - iso: eng month: '08' oa_version: None page: 1295 - 1308 publication: IEEE Transactions on Circuits and Systems for Video Technology publication_status: published publisher: IEEE publist_id: '5638' quality_controlled: '1' scopus_import: 1 status: public title: Segmentation over detection via optimal sparse reconstructions type: journal_article user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 25 year: '2015' ... --- _id: '1570' abstract: - lang: eng text: Grounding autonomous behavior in the nervous system is a fundamental challenge for neuroscience. In particular, self-organized behavioral development provides more questions than answers. Are there special functional units for curiosity, motivation, and creativity? This paper argues that these features can be grounded in synaptic plasticity itself, without requiring any higher-level constructs. We propose differential extrinsic plasticity (DEP) as a new synaptic rule for self-learning systems and apply it to a number of complex robotic systems as a test case. Without specifying any purpose or goal, seemingly purposeful and adaptive rhythmic behavior is developed, displaying a certain level of sensorimotor intelligence. These surprising results require no systemspecific modifications of the DEP rule. They rather arise from the underlying mechanism of spontaneous symmetry breaking,which is due to the tight brain body environment coupling. The new synaptic rule is biologically plausible and would be an interesting target for neurobiological investigation. We also argue that this neuronal mechanism may have been a catalyst in natural evolution. author: - first_name: Ralf full_name: Der, Ralf last_name: Der - first_name: Georg S full_name: Martius, Georg S id: 3A276B68-F248-11E8-B48F-1D18A9856A87 last_name: Martius citation: ama: Der R, Martius GS. Novel plasticity rule can explain the development of sensorimotor intelligence. PNAS. 2015;112(45):E6224-E6232. doi:10.1073/pnas.1508400112 apa: Der, R., & Martius, G. S. (2015). Novel plasticity rule can explain the development of sensorimotor intelligence. PNAS. National Academy of Sciences. https://doi.org/10.1073/pnas.1508400112 chicago: Der, Ralf, and Georg S Martius. “Novel Plasticity Rule Can Explain the Development of Sensorimotor Intelligence.” PNAS. National Academy of Sciences, 2015. https://doi.org/10.1073/pnas.1508400112. ieee: R. Der and G. S. Martius, “Novel plasticity rule can explain the development of sensorimotor intelligence,” PNAS, vol. 112, no. 45. National Academy of Sciences, pp. E6224–E6232, 2015. ista: Der R, Martius GS. 2015. Novel plasticity rule can explain the development of sensorimotor intelligence. PNAS. 112(45), E6224–E6232. mla: Der, Ralf, and Georg S. Martius. “Novel Plasticity Rule Can Explain the Development of Sensorimotor Intelligence.” PNAS, vol. 112, no. 45, National Academy of Sciences, 2015, pp. E6224–32, doi:10.1073/pnas.1508400112. short: R. Der, G.S. Martius, PNAS 112 (2015) E6224–E6232. date_created: 2018-12-11T11:52:47Z date_published: 2015-11-10T00:00:00Z date_updated: 2021-01-12T06:51:40Z day: '10' department: - _id: ChLa - _id: GaTk doi: 10.1073/pnas.1508400112 ec_funded: 1 external_id: pmid: - '26504200' intvolume: ' 112' issue: '45' language: - iso: eng main_file_link: - open_access: '1' url: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4653169/ month: '11' oa: 1 oa_version: Submitted Version page: E6224 - E6232 pmid: 1 project: - _id: 25681D80-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '291734' name: International IST Postdoc Fellowship Programme publication: PNAS publication_status: published publisher: National Academy of Sciences publist_id: '5601' quality_controlled: '1' scopus_import: 1 status: public title: Novel plasticity rule can explain the development of sensorimotor intelligence type: journal_article user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 112 year: '2015' ... --- _id: '1706' abstract: - lang: eng text: We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneously is beneficial over single task learning. In particular, as the number of observed tasks grows, assuming that in the considered family of kernels there exists one that yields low approximation error on all tasks, the overhead associated with learning such a kernel vanishes and the complexity converges to that of learning when this good kernel is given to the learner. alternative_title: - LNCS author: - first_name: Anastasia full_name: Pentina, Anastasia id: 42E87FC6-F248-11E8-B48F-1D18A9856A87 last_name: Pentina - first_name: Shai full_name: Ben David, Shai last_name: Ben David citation: ama: 'Pentina A, Ben David S. Multi-task and lifelong learning of kernels. In: Vol 9355. Springer; 2015:194-208. doi:10.1007/978-3-319-24486-0_13' apa: 'Pentina, A., & Ben David, S. (2015). Multi-task and lifelong learning of kernels (Vol. 9355, pp. 194–208). Presented at the ALT: Algorithmic Learning Theory, Banff, AB, Canada: Springer. https://doi.org/10.1007/978-3-319-24486-0_13' chicago: Pentina, Anastasia, and Shai Ben David. “Multi-Task and Lifelong Learning of Kernels,” 9355:194–208. Springer, 2015. https://doi.org/10.1007/978-3-319-24486-0_13. ieee: 'A. Pentina and S. Ben David, “Multi-task and lifelong learning of kernels,” presented at the ALT: Algorithmic Learning Theory, Banff, AB, Canada, 2015, vol. 9355, pp. 194–208.' ista: 'Pentina A, Ben David S. 2015. Multi-task and lifelong learning of kernels. ALT: Algorithmic Learning Theory, LNCS, vol. 9355, 194–208.' mla: Pentina, Anastasia, and Shai Ben David. Multi-Task and Lifelong Learning of Kernels. Vol. 9355, Springer, 2015, pp. 194–208, doi:10.1007/978-3-319-24486-0_13. short: A. Pentina, S. Ben David, in:, Springer, 2015, pp. 194–208. conference: end_date: 2015-10-06 location: Banff, AB, Canada name: 'ALT: Algorithmic Learning Theory' start_date: 2015-10-04 date_created: 2018-12-11T11:53:35Z date_published: 2015-01-01T00:00:00Z date_updated: 2021-01-12T06:52:39Z day: '01' department: - _id: ChLa doi: 10.1007/978-3-319-24486-0_13 ec_funded: 1 intvolume: ' 9355' language: - iso: eng main_file_link: - open_access: '1' url: http://arxiv.org/abs/1602.06531 month: '01' oa: 1 oa_version: Preprint page: 194 - 208 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication_status: published publisher: Springer publist_id: '5430' quality_controlled: '1' scopus_import: 1 status: public title: Multi-task and lifelong learning of kernels type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 9355 year: '2015' ... --- _id: '1859' abstract: - lang: eng text: "Structural support vector machines (SSVMs) are amongst the best performing models for structured computer vision tasks, such as semantic image segmentation or human pose estimation. Training SSVMs, however, is computationally costly, because it requires repeated calls to a structured prediction subroutine (called \\emph{max-oracle}), which has to solve an optimization problem itself, e.g. a graph cut.\r\nIn this work, we introduce a new algorithm for SSVM training that is more efficient than earlier techniques when the max-oracle is computationally expensive, as it is frequently the case in computer vision tasks. The main idea is to (i) combine the recent stochastic Block-Coordinate Frank-Wolfe algorithm with efficient hyperplane caching, and (ii) use an automatic selection rule for deciding whether to call the exact max-oracle or to rely on an approximate one based on the cached hyperplanes.\r\nWe show experimentally that this strategy leads to faster convergence to the optimum with respect to the number of requires oracle calls, and that this translates into faster convergence with respect to the total runtime when the max-oracle is slow compared to the other steps of the algorithm. " author: - first_name: Neel full_name: Shah, Neel id: 31ABAF80-F248-11E8-B48F-1D18A9856A87 last_name: Shah - first_name: Vladimir full_name: Kolmogorov, Vladimir id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87 last_name: Kolmogorov - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Shah N, Kolmogorov V, Lampert C. A multi-plane block-coordinate Frank-Wolfe algorithm for training structural SVMs with a costly max-oracle. In: IEEE; 2015:2737-2745. doi:10.1109/CVPR.2015.7298890' apa: 'Shah, N., Kolmogorov, V., & Lampert, C. (2015). A multi-plane block-coordinate Frank-Wolfe algorithm for training structural SVMs with a costly max-oracle (pp. 2737–2745). Presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, USA: IEEE. https://doi.org/10.1109/CVPR.2015.7298890' chicago: Shah, Neel, Vladimir Kolmogorov, and Christoph Lampert. “A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs with a Costly Max-Oracle,” 2737–45. IEEE, 2015. https://doi.org/10.1109/CVPR.2015.7298890. ieee: 'N. Shah, V. Kolmogorov, and C. Lampert, “A multi-plane block-coordinate Frank-Wolfe algorithm for training structural SVMs with a costly max-oracle,” presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, USA, 2015, pp. 2737–2745.' ista: 'Shah N, Kolmogorov V, Lampert C. 2015. A multi-plane block-coordinate Frank-Wolfe algorithm for training structural SVMs with a costly max-oracle. CVPR: Computer Vision and Pattern Recognition, 2737–2745.' mla: Shah, Neel, et al. A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs with a Costly Max-Oracle. IEEE, 2015, pp. 2737–45, doi:10.1109/CVPR.2015.7298890. short: N. Shah, V. Kolmogorov, C. Lampert, in:, IEEE, 2015, pp. 2737–2745. conference: end_date: 2015-06-12 location: Boston, MA, USA name: 'CVPR: Computer Vision and Pattern Recognition' start_date: 2015-06-07 date_created: 2018-12-11T11:54:24Z date_published: 2015-06-01T00:00:00Z date_updated: 2021-01-12T06:53:40Z day: '01' department: - _id: VlKo - _id: ChLa doi: 10.1109/CVPR.2015.7298890 ec_funded: 1 language: - iso: eng main_file_link: - open_access: '1' url: http://arxiv.org/abs/1408.6804 month: '06' oa: 1 oa_version: Preprint page: 2737 - 2745 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding - _id: 25FBA906-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '616160' name: 'Discrete Optimization in Computer Vision: Theory and Practice' publication_status: published publisher: IEEE publist_id: '5240' quality_controlled: '1' scopus_import: 1 status: public title: A multi-plane block-coordinate Frank-Wolfe algorithm for training structural SVMs with a costly max-oracle type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2015' ... --- _id: '1860' abstract: - lang: eng text: Classifiers for object categorization are usually evaluated by their accuracy on a set of i.i.d. test examples. This provides us with an estimate of the expected error when applying the classifiers to a single new image. In real application, however, classifiers are rarely only used for a single image and then discarded. Instead, they are applied sequentially to many images, and these are typically not i.i.d. samples from a fixed data distribution, but they carry dependencies and their class distribution varies over time. In this work, we argue that the phenomenon of correlated data at prediction time is not a nuisance, but a blessing in disguise. We describe a probabilistic method for adapting classifiers at prediction time without having to retrain them. We also introduce a framework for creating realistically distributed image sequences, which offers a way to benchmark classifier adaptation methods, such as the one we propose. Experiments on the ILSVRC2010 and ILSVRC2012 datasets show that adapting object classification systems at prediction time can significantly reduce their error rate, even with no additional human feedback. author: - first_name: Amélie full_name: Royer, Amélie last_name: Royer - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Royer A, Lampert C. Classifier adaptation at prediction time. In: IEEE; 2015:1401-1409. doi:10.1109/CVPR.2015.7298746' apa: 'Royer, A., & Lampert, C. (2015). Classifier adaptation at prediction time (pp. 1401–1409). Presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, United States: IEEE. https://doi.org/10.1109/CVPR.2015.7298746' chicago: Royer, Amélie, and Christoph Lampert. “Classifier Adaptation at Prediction Time,” 1401–9. IEEE, 2015. https://doi.org/10.1109/CVPR.2015.7298746. ieee: 'A. Royer and C. Lampert, “Classifier adaptation at prediction time,” presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, United States, 2015, pp. 1401–1409.' ista: 'Royer A, Lampert C. 2015. Classifier adaptation at prediction time. CVPR: Computer Vision and Pattern Recognition, 1401–1409.' mla: Royer, Amélie, and Christoph Lampert. Classifier Adaptation at Prediction Time. IEEE, 2015, pp. 1401–09, doi:10.1109/CVPR.2015.7298746. short: A. Royer, C. Lampert, in:, IEEE, 2015, pp. 1401–1409. conference: end_date: 2015-06-12 location: Boston, MA, United States name: 'CVPR: Computer Vision and Pattern Recognition' start_date: 2015-06-07 date_created: 2018-12-11T11:54:24Z date_published: 2015-06-01T00:00:00Z date_updated: 2021-01-12T06:53:41Z day: '01' department: - _id: ChLa doi: 10.1109/CVPR.2015.7298746 ec_funded: 1 language: - iso: eng main_file_link: - open_access: '1' url: http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Royer_Classifier_Adaptation_at_2015_CVPR_paper.pdf month: '06' oa: 1 oa_version: Submitted Version page: 1401 - 1409 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication_status: published publisher: IEEE publist_id: '5239' quality_controlled: '1' scopus_import: 1 status: public title: Classifier adaptation at prediction time type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2015' ... --- _id: '1858' abstract: - lang: eng text: 'We study the problem of predicting the future, though only in the probabilistic sense of estimating a future state of a time-varying probability distribution. This is not only an interesting academic problem, but solving this extrapolation problem also has many practical application, e.g. for training classifiers that have to operate under time-varying conditions. Our main contribution is a method for predicting the next step of the time-varying distribution from a given sequence of sample sets from earlier time steps. For this we rely on two recent machine learning techniques: embedding probability distributions into a reproducing kernel Hilbert space, and learning operators by vector-valued regression. We illustrate the working principles and the practical usefulness of our method by experiments on synthetic and real data. We also highlight an exemplary application: training a classifier in a domain adaptation setting without having access to examples from the test time distribution at training time.' author: - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Lampert C. Predicting the future behavior of a time-varying probability distribution. In: IEEE; 2015:942-950. doi:10.1109/CVPR.2015.7298696' apa: 'Lampert, C. (2015). Predicting the future behavior of a time-varying probability distribution (pp. 942–950). Presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, United States: IEEE. https://doi.org/10.1109/CVPR.2015.7298696' chicago: Lampert, Christoph. “Predicting the Future Behavior of a Time-Varying Probability Distribution,” 942–50. IEEE, 2015. https://doi.org/10.1109/CVPR.2015.7298696. ieee: 'C. Lampert, “Predicting the future behavior of a time-varying probability distribution,” presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, United States, 2015, pp. 942–950.' ista: 'Lampert C. 2015. Predicting the future behavior of a time-varying probability distribution. CVPR: Computer Vision and Pattern Recognition, 942–950.' mla: Lampert, Christoph. Predicting the Future Behavior of a Time-Varying Probability Distribution. IEEE, 2015, pp. 942–50, doi:10.1109/CVPR.2015.7298696. short: C. Lampert, in:, IEEE, 2015, pp. 942–950. conference: end_date: 2015-06-12 location: Boston, MA, United States name: 'CVPR: Computer Vision and Pattern Recognition' start_date: 2015-06-07 date_created: 2018-12-11T11:54:24Z date_published: 2015-10-15T00:00:00Z date_updated: 2021-01-12T06:53:40Z day: '15' department: - _id: ChLa doi: 10.1109/CVPR.2015.7298696 external_id: arxiv: - '1406.5362' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/1406.5362 month: '10' oa: 1 oa_version: Preprint page: 942 - 950 publication_status: published publisher: IEEE publist_id: '5241' quality_controlled: '1' scopus_import: 1 status: public title: Predicting the future behavior of a time-varying probability distribution type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2015' ... --- _id: '1857' abstract: - lang: eng text: 'Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between the most related tasks. In this work we propose an approach that processes multiple tasks in a sequence with sharing between subsequent tasks instead of solving all tasks jointly. Subsequently, we address the question of curriculum learning of tasks, i.e. finding the best order of tasks to be learned. Our approach is based on a generalization bound criterion for choosing the task order that optimizes the average expected classification performance over all tasks. Our experimental results show that learning multiple related tasks sequentially can be more effective than learning them jointly, the order in which tasks are being solved affects the overall performance, and that our model is able to automatically discover the favourable order of tasks. ' author: - first_name: Anastasia full_name: Pentina, Anastasia id: 42E87FC6-F248-11E8-B48F-1D18A9856A87 last_name: Pentina - first_name: Viktoriia full_name: Sharmanska, Viktoriia id: 2EA6D09E-F248-11E8-B48F-1D18A9856A87 last_name: Sharmanska orcid: 0000-0003-0192-9308 - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Pentina A, Sharmanska V, Lampert C. Curriculum learning of multiple tasks. In: IEEE; 2015:5492-5500. doi:10.1109/CVPR.2015.7299188' apa: 'Pentina, A., Sharmanska, V., & Lampert, C. (2015). Curriculum learning of multiple tasks (pp. 5492–5500). Presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, United States: IEEE. https://doi.org/10.1109/CVPR.2015.7299188' chicago: Pentina, Anastasia, Viktoriia Sharmanska, and Christoph Lampert. “Curriculum Learning of Multiple Tasks,” 5492–5500. IEEE, 2015. https://doi.org/10.1109/CVPR.2015.7299188. ieee: 'A. Pentina, V. Sharmanska, and C. Lampert, “Curriculum learning of multiple tasks,” presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, United States, 2015, pp. 5492–5500.' ista: 'Pentina A, Sharmanska V, Lampert C. 2015. Curriculum learning of multiple tasks. CVPR: Computer Vision and Pattern Recognition, 5492–5500.' mla: Pentina, Anastasia, et al. Curriculum Learning of Multiple Tasks. IEEE, 2015, pp. 5492–500, doi:10.1109/CVPR.2015.7299188. short: A. Pentina, V. Sharmanska, C. Lampert, in:, IEEE, 2015, pp. 5492–5500. conference: end_date: 2015-06-12 location: Boston, MA, United States name: 'CVPR: Computer Vision and Pattern Recognition' start_date: 2015-06-07 date_created: 2018-12-11T11:54:23Z date_published: 2015-06-01T00:00:00Z date_updated: 2023-02-23T10:17:31Z day: '01' department: - _id: ChLa doi: 10.1109/CVPR.2015.7299188 language: - iso: eng main_file_link: - open_access: '1' url: http://arxiv.org/abs/1412.1353 month: '06' oa: 1 oa_version: Preprint page: 5492 - 5500 publication_status: published publisher: IEEE publist_id: '5243' quality_controlled: '1' scopus_import: 1 status: public title: Curriculum learning of multiple tasks type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2015' ... --- _id: '12881' acknowledgement: This work was supported by the DFG (SPP 1527) and the EU (FP7, REA grant no 291734). article_processing_charge: No author: - first_name: Georg S full_name: Martius, Georg S id: 3A276B68-F248-11E8-B48F-1D18A9856A87 last_name: Martius - first_name: Eckehard full_name: Olbrich, Eckehard last_name: Olbrich citation: ama: 'Martius GS, Olbrich E. Quantifying self-organizing behavior of autonomous robots. In: Proceedings of the 13th European Conference on Artificial Life. MIT Press; 2015:78. doi:10.7551/978-0-262-33027-5-ch018' apa: 'Martius, G. S., & Olbrich, E. (2015). Quantifying self-organizing behavior of autonomous robots. In Proceedings of the 13th European Conference on Artificial Life (p. 78). York, United Kingdom: MIT Press. https://doi.org/10.7551/978-0-262-33027-5-ch018' chicago: Martius, Georg S, and Eckehard Olbrich. “Quantifying Self-Organizing Behavior of Autonomous Robots.” In Proceedings of the 13th European Conference on Artificial Life, 78. MIT Press, 2015. https://doi.org/10.7551/978-0-262-33027-5-ch018. ieee: G. S. Martius and E. Olbrich, “Quantifying self-organizing behavior of autonomous robots,” in Proceedings of the 13th European Conference on Artificial Life, York, United Kingdom, 2015, p. 78. ista: 'Martius GS, Olbrich E. 2015. Quantifying self-organizing behavior of autonomous robots. Proceedings of the 13th European Conference on Artificial Life. ECAL: European Conference on Artificial Life, 78.' mla: Martius, Georg S., and Eckehard Olbrich. “Quantifying Self-Organizing Behavior of Autonomous Robots.” Proceedings of the 13th European Conference on Artificial Life, MIT Press, 2015, p. 78, doi:10.7551/978-0-262-33027-5-ch018. short: G.S. Martius, E. Olbrich, in:, Proceedings of the 13th European Conference on Artificial Life, MIT Press, 2015, p. 78. conference: end_date: 2015-07-24 location: York, United Kingdom name: 'ECAL: European Conference on Artificial Life' start_date: 2015-07-20 date_created: 2023-04-30T22:01:07Z date_published: 2015-07-01T00:00:00Z date_updated: 2023-05-02T07:06:21Z day: '01' ddc: - '000' department: - _id: ChLa doi: 10.7551/978-0-262-33027-5-ch018 ec_funded: 1 file: - access_level: open_access checksum: 880eabe59c9df12f06a882aa1bc4e600 content_type: application/pdf creator: dernst date_created: 2023-05-02T07:02:59Z date_updated: 2023-05-02T07:02:59Z file_id: '12882' file_name: 2015_ECAL_Martius.pdf file_size: 1674241 relation: main_file success: 1 file_date_updated: 2023-05-02T07:02:59Z has_accepted_license: '1' language: - iso: eng month: '07' oa: 1 oa_version: Published Version page: '78' project: - _id: 25681D80-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '291734' name: International IST Postdoc Fellowship Programme publication: Proceedings of the 13th European Conference on Artificial Life publication_identifier: isbn: - '9780262330275' publication_status: published publisher: MIT Press quality_controlled: '1' scopus_import: '1' status: public title: Quantifying self-organizing behavior of autonomous robots tmp: image: /images/cc_by.png legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0) short: CC BY (4.0) type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2015' ... --- _id: '1401' abstract: - lang: eng text: 'The human ability to recognize objects in complex scenes has driven research in the computer vision field over couple of decades. This thesis focuses on the object recognition task in images. That is, given the image, we want the computer system to be able to predict the class of the object that appears in the image. A recent successful attempt to bridge semantic understanding of the image perceived by humans and by computers uses attribute-based models. Attributes are semantic properties of the objects shared across different categories, which humans and computers can decide on. To explore the attribute-based models we take a statistical machine learning approach, and address two key learning challenges in view of object recognition task: learning augmented attributes as mid-level discriminative feature representation, and learning with attributes as privileged information. Our main contributions are parametric and non-parametric models and algorithms to solve these frameworks. In the parametric approach, we explore an autoencoder model combined with the large margin nearest neighbor principle for mid-level feature learning, and linear support vector machines for learning with privileged information. In the non-parametric approach, we propose a supervised Indian Buffet Process for automatic augmentation of semantic attributes, and explore the Gaussian Processes classification framework for learning with privileged information. A thorough experimental analysis shows the effectiveness of the proposed models in both parametric and non-parametric views.' acknowledgement: "I would like to thank my supervisor, Christoph Lampert, for guidance throughout my studies and for patience in transforming me into a scientist, and my thesis committee, Chris Wojtan and Horst Bischof, for their help and advice. \r\n\r\nI would like to thank Elisabeth Hacker who perfectly assisted all my administrative needs and was always nice and friendly to me, and the campus team for making the IST Austria campus my second home. \r\nI was honored to collaborate with brilliant researchers and to learn from their experience. Undoubtedly, I learned most of all from Novi Quadrianto: brainstorming our projects and getting exciting results was the most enjoyable part of my work – thank you! I am also grateful to David Knowles, Zoubin Ghahramani, Daniel Hernández-Lobato, Kristian Kersting and Anastasia Pentina for the fantastic projects we worked on together, and to Kristen Grauman and Adriana Kovashka for the exceptional experience working with user studies. I would like to thank my colleagues at IST Austria and my office mates who shared their happy moods, scientific breakthroughs and thought-provoking conversations with me: Chao, Filip, Rustem, Asya, Sameh, Alex, Vlad, Mayu, Neel, Csaba, Thomas, Vladimir, Cristina, Alex Z., Avro, Amelie and Emilie, Andreas H. and Andreas E., Chris, Lena, Michael, Ali and Ipek, Vera, Igor, Katia. Special thanks to Morten for the countless games of table soccer we played together and the tournaments we teamed up for: we will definitely win next time:) A very warm hug to Asya for always being so inspiring and supportive to me, and for helping me to increase the proportion of female computer scientists in our group. " alternative_title: - ISTA Thesis article_processing_charge: No author: - first_name: Viktoriia full_name: Sharmanska, Viktoriia id: 2EA6D09E-F248-11E8-B48F-1D18A9856A87 last_name: Sharmanska orcid: 0000-0003-0192-9308 citation: ama: 'Sharmanska V. Learning with attributes for object recognition: Parametric and non-parametrics views. 2015. doi:10.15479/at:ista:1401' apa: 'Sharmanska, V. (2015). Learning with attributes for object recognition: Parametric and non-parametrics views. Institute of Science and Technology Austria. https://doi.org/10.15479/at:ista:1401' chicago: 'Sharmanska, Viktoriia. “Learning with Attributes for Object Recognition: Parametric and Non-Parametrics Views.” Institute of Science and Technology Austria, 2015. https://doi.org/10.15479/at:ista:1401.' ieee: 'V. Sharmanska, “Learning with attributes for object recognition: Parametric and non-parametrics views,” Institute of Science and Technology Austria, 2015.' ista: 'Sharmanska V. 2015. Learning with attributes for object recognition: Parametric and non-parametrics views. Institute of Science and Technology Austria.' mla: 'Sharmanska, Viktoriia. Learning with Attributes for Object Recognition: Parametric and Non-Parametrics Views. Institute of Science and Technology Austria, 2015, doi:10.15479/at:ista:1401.' short: 'V. Sharmanska, Learning with Attributes for Object Recognition: Parametric and Non-Parametrics Views, Institute of Science and Technology Austria, 2015.' date_created: 2018-12-11T11:51:48Z date_published: 2015-04-01T00:00:00Z date_updated: 2023-09-07T11:40:11Z day: '01' ddc: - '000' degree_awarded: PhD department: - _id: ChLa - _id: GradSch doi: 10.15479/at:ista:1401 file: - access_level: open_access checksum: 3605b402bb6934e09ae4cf672c84baf7 content_type: application/pdf creator: dernst date_created: 2021-02-22T11:33:17Z date_updated: 2021-02-22T11:33:17Z file_id: '9177' file_name: 2015_Thesis_Sharmanska.pdf file_size: 7964342 relation: main_file success: 1 - access_level: closed checksum: e37593b3ee75bf3180629df2d6ca8f4e content_type: application/pdf creator: cchlebak date_created: 2021-11-16T14:40:45Z date_updated: 2021-11-17T13:47:24Z file_id: '10297' file_name: 2015_Thesis_Sharmanska_pdfa.pdf file_size: 7372241 relation: main_file file_date_updated: 2021-11-17T13:47:24Z has_accepted_license: '1' language: - iso: eng main_file_link: - url: http://users.sussex.ac.uk/~nq28/viktoriia/Thesis_Sharmanska.pdf month: '04' oa: 1 oa_version: Published Version page: '144' publication_identifier: issn: - 2663-337X publication_status: published publisher: Institute of Science and Technology Austria publist_id: '5806' status: public supervisor: - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 title: 'Learning with attributes for object recognition: Parametric and non-parametrics views' type: dissertation user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1 year: '2015' ... --- _id: '1655' abstract: - lang: eng text: Quantifying behaviors of robots which were generated autonomously from task-independent objective functions is an important prerequisite for objective comparisons of algorithms and movements of animals. The temporal sequence of such a behavior can be considered as a time series and hence complexity measures developed for time series are natural candidates for its quantification. The predictive information and the excess entropy are such complexity measures. They measure the amount of information the past contains about the future and thus quantify the nonrandom structure in the temporal sequence. However, when using these measures for systems with continuous states one has to deal with the fact that their values will depend on the resolution with which the systems states are observed. For deterministic systems both measures will diverge with increasing resolution. We therefore propose a new decomposition of the excess entropy in resolution dependent and resolution independent parts and discuss how they depend on the dimensionality of the dynamics, correlations and the noise level. For the practical estimation we propose to use estimates based on the correlation integral instead of the direct estimation of the mutual information based on next neighbor statistics because the latter allows less control of the scale dependencies. Using our algorithm we are able to show how autonomous learning generates behavior of increasing complexity with increasing learning duration. acknowledgement: This work was supported by the DFG priority program 1527 (Autonomous Learning) and by the European Community’s Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 318723 (MatheMACS) and from the People Programme (Marie Curie Actions) of the European Union’s Seventh Framework Programme (FP7/2007-2013) under REA grant agreement no. 291734. article_processing_charge: No author: - first_name: Georg S full_name: Martius, Georg S id: 3A276B68-F248-11E8-B48F-1D18A9856A87 last_name: Martius - first_name: Eckehard full_name: Olbrich, Eckehard last_name: Olbrich citation: ama: Martius GS, Olbrich E. Quantifying emergent behavior of autonomous robots. Entropy. 2015;17(10):7266-7297. doi:10.3390/e17107266 apa: Martius, G. S., & Olbrich, E. (2015). Quantifying emergent behavior of autonomous robots. Entropy. MDPI. https://doi.org/10.3390/e17107266 chicago: Martius, Georg S, and Eckehard Olbrich. “Quantifying Emergent Behavior of Autonomous Robots.” Entropy. MDPI, 2015. https://doi.org/10.3390/e17107266. ieee: G. S. Martius and E. Olbrich, “Quantifying emergent behavior of autonomous robots,” Entropy, vol. 17, no. 10. MDPI, pp. 7266–7297, 2015. ista: Martius GS, Olbrich E. 2015. Quantifying emergent behavior of autonomous robots. Entropy. 17(10), 7266–7297. mla: Martius, Georg S., and Eckehard Olbrich. “Quantifying Emergent Behavior of Autonomous Robots.” Entropy, vol. 17, no. 10, MDPI, 2015, pp. 7266–97, doi:10.3390/e17107266. short: G.S. Martius, E. Olbrich, Entropy 17 (2015) 7266–7297. date_created: 2018-12-11T11:53:17Z date_published: 2015-10-23T00:00:00Z date_updated: 2023-10-17T11:42:00Z day: '23' ddc: - '000' department: - _id: ChLa - _id: GaTk doi: 10.3390/e17107266 ec_funded: 1 file: - access_level: open_access checksum: 945d99631a96e0315acb26dc8541dcf9 content_type: application/pdf creator: system date_created: 2018-12-12T10:12:25Z date_updated: 2020-07-14T12:45:08Z file_id: '4943' file_name: IST-2016-464-v1+1_entropy-17-07266.pdf file_size: 6455007 relation: main_file file_date_updated: 2020-07-14T12:45:08Z has_accepted_license: '1' intvolume: ' 17' issue: '10' language: - iso: eng month: '10' oa: 1 oa_version: Published Version page: 7266 - 7297 project: - _id: 25681D80-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '291734' name: International IST Postdoc Fellowship Programme publication: Entropy publication_status: published publisher: MDPI publist_id: '5495' pubrep_id: '464' quality_controlled: '1' scopus_import: '1' status: public title: Quantifying emergent behavior of autonomous robots tmp: image: /images/cc_by.png legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0) short: CC BY (4.0) type: journal_article user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 17 year: '2015' ... --- _id: '1829' abstract: - lang: eng text: Hitting and batting tasks, such as tennis forehands, ping-pong strokes, or baseball batting, depend on predictions where the ball can be intercepted and how it can properly be returned to the opponent. These predictions get more accurate over time, hence the behaviors need to be continuously modified. As a result, movement templates with a learned global shape need to be adapted during the execution so that the racket reaches a target position and velocity that will return the ball over to the other side of the net or court. It requires altering learned movements to hit a varying target with the necessary velocity at a specific instant in time. Such a task cannot be incorporated straightforwardly in most movement representations suitable for learning. For example, the standard formulation of the dynamical system based motor primitives (introduced by Ijspeert et al (2002b)) does not satisfy this property despite their flexibility which has allowed learning tasks ranging from locomotion to kendama. In order to fulfill this requirement, we reformulate the Ijspeert framework to incorporate the possibility of specifying a desired hitting point and a desired hitting velocity while maintaining all advantages of the original formulation.We show that the proposed movement template formulation works well in two scenarios, i.e., for hitting a ball on a string with a table tennis racket at a specified velocity and for returning balls launched by a ball gun successfully over the net using forehand movements. alternative_title: - Springer Tracts in Advanced Robotics author: - first_name: Katharina full_name: Muelling, Katharina last_name: Muelling - first_name: Oliver full_name: Kroemer, Oliver last_name: Kroemer - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 - first_name: Bernhard full_name: Schölkopf, Bernhard last_name: Schölkopf citation: ama: 'Muelling K, Kroemer O, Lampert C, Schölkopf B. Movement templates for learning of hitting and batting. In: Kober J, Peters J, eds. Learning Motor Skills. Vol 97. From Algorithms to Robot Experiments. Springer; 2014:69-82. doi:10.1007/978-3-319-03194-1_3' apa: Muelling, K., Kroemer, O., Lampert, C., & Schölkopf, B. (2014). Movement templates for learning of hitting and batting. In J. Kober & J. Peters (Eds.), Learning Motor Skills (Vol. 97, pp. 69–82). Springer. https://doi.org/10.1007/978-3-319-03194-1_3 chicago: Muelling, Katharina, Oliver Kroemer, Christoph Lampert, and Bernhard Schölkopf. “Movement Templates for Learning of Hitting and Batting.” In Learning Motor Skills, edited by Jens Kober and Jan Peters, 97:69–82. From Algorithms to Robot Experiments. Springer, 2014. https://doi.org/10.1007/978-3-319-03194-1_3. ieee: K. Muelling, O. Kroemer, C. Lampert, and B. Schölkopf, “Movement templates for learning of hitting and batting,” in Learning Motor Skills, vol. 97, J. Kober and J. Peters, Eds. Springer, 2014, pp. 69–82. ista: 'Muelling K, Kroemer O, Lampert C, Schölkopf B. 2014.Movement templates for learning of hitting and batting. In: Learning Motor Skills. Springer Tracts in Advanced Robotics, vol. 97, 69–82.' mla: Muelling, Katharina, et al. “Movement Templates for Learning of Hitting and Batting.” Learning Motor Skills, edited by Jens Kober and Jan Peters, vol. 97, Springer, 2014, pp. 69–82, doi:10.1007/978-3-319-03194-1_3. short: K. Muelling, O. Kroemer, C. Lampert, B. Schölkopf, in:, J. Kober, J. Peters (Eds.), Learning Motor Skills, Springer, 2014, pp. 69–82. date_created: 2018-12-11T11:54:14Z date_published: 2014-01-01T00:00:00Z date_updated: 2021-01-12T06:53:28Z day: '01' department: - _id: ChLa doi: 10.1007/978-3-319-03194-1_3 editor: - first_name: Jens full_name: Kober, Jens last_name: Kober - first_name: Jan full_name: Peters, Jan last_name: Peters intvolume: ' 97' language: - iso: eng month: '01' oa_version: None page: 69 - 82 publication: Learning Motor Skills publication_status: published publisher: Springer publist_id: '5274' quality_controlled: '1' scopus_import: 1 series_title: From Algorithms to Robot Experiments status: public title: Movement templates for learning of hitting and batting type: book_chapter user_id: 4435EBFC-F248-11E8-B48F-1D18A9856A87 volume: 97 year: '2014' ... --- _id: '2033' abstract: - lang: eng text: 'The learning with privileged information setting has recently attracted a lot of attention within the machine learning community, as it allows the integration of additional knowledge into the training process of a classifier, even when this comes in the form of a data modality that is not available at test time. Here, we show that privileged information can naturally be treated as noise in the latent function of a Gaussian process classifier (GPC). That is, in contrast to the standard GPC setting, the latent function is not just a nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC probit likelihood function. Extensive experiments on public datasets show that the proposed GPC method using privileged noise, called GPC+, improves over a standard GPC without privileged knowledge, and also over the current state-of-the-art SVM-based method, SVM+. Moreover, we show that advanced neural networks and deep learning methods can be compressed as privileged information.' author: - first_name: Daniel full_name: Hernandez Lobato, Daniel last_name: Hernandez Lobato - first_name: Viktoriia full_name: Sharmanska, Viktoriia id: 2EA6D09E-F248-11E8-B48F-1D18A9856A87 last_name: Sharmanska orcid: 0000-0003-0192-9308 - first_name: Kristian full_name: Kersting, Kristian last_name: Kersting - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 - first_name: Novi full_name: Quadrianto, Novi last_name: Quadrianto citation: ama: 'Hernandez Lobato D, Sharmanska V, Kersting K, Lampert C, Quadrianto N. Mind the nuisance: Gaussian process classification using privileged noise. In: Advances in Neural Information Processing Systems. Vol 1. Neural Information Processing Systems; 2014:837-845.' apa: 'Hernandez Lobato, D., Sharmanska, V., Kersting, K., Lampert, C., & Quadrianto, N. (2014). Mind the nuisance: Gaussian process classification using privileged noise. In Advances in Neural Information Processing Systems (Vol. 1, pp. 837–845). Montreal, Canada: Neural Information Processing Systems.' chicago: 'Hernandez Lobato, Daniel, Viktoriia Sharmanska, Kristian Kersting, Christoph Lampert, and Novi Quadrianto. “Mind the Nuisance: Gaussian Process Classification Using Privileged Noise.” In Advances in Neural Information Processing Systems, 1:837–45. Neural Information Processing Systems, 2014.' ieee: 'D. Hernandez Lobato, V. Sharmanska, K. Kersting, C. Lampert, and N. Quadrianto, “Mind the nuisance: Gaussian process classification using privileged noise,” in Advances in Neural Information Processing Systems, Montreal, Canada, 2014, vol. 1, no. January, pp. 837–845.' ista: 'Hernandez Lobato D, Sharmanska V, Kersting K, Lampert C, Quadrianto N. 2014. Mind the nuisance: Gaussian process classification using privileged noise. Advances in Neural Information Processing Systems. NIPS: Neural Information Processing Systems vol. 1, 837–845.' mla: 'Hernandez Lobato, Daniel, et al. “Mind the Nuisance: Gaussian Process Classification Using Privileged Noise.” Advances in Neural Information Processing Systems, vol. 1, no. January, Neural Information Processing Systems, 2014, pp. 837–45.' short: D. Hernandez Lobato, V. Sharmanska, K. Kersting, C. Lampert, N. Quadrianto, in:, Advances in Neural Information Processing Systems, Neural Information Processing Systems, 2014, pp. 837–845. conference: end_date: 2014-12-13 location: Montreal, Canada name: 'NIPS: Neural Information Processing Systems' start_date: 2014-12-08 date_created: 2018-12-11T11:55:20Z date_published: 2014-12-08T00:00:00Z date_updated: 2023-02-23T10:25:24Z day: '08' department: - _id: ChLa intvolume: ' 1' issue: January language: - iso: eng main_file_link: - open_access: '1' url: https://papers.nips.cc/paper/5373-mind-the-nuisance-gaussian-process-classification-using-privileged-noise month: '12' oa: 1 oa_version: Submitted Version page: 837-845 publication: Advances in Neural Information Processing Systems publication_status: published publisher: Neural Information Processing Systems publist_id: '5038' quality_controlled: '1' scopus_import: 1 status: public title: 'Mind the nuisance: Gaussian process classification using privileged noise' type: conference user_id: 4435EBFC-F248-11E8-B48F-1D18A9856A87 volume: 1 year: '2014' ...