TY - CONF AB - 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. AU - Pentina, Anastasia AU - Urner, Ruth ID - 1098 TI - Lifelong learning with weighted majority votes VL - 29 ER - TY - CONF AB - 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. AU - Kolesnikov, Alexander AU - Lampert, Christoph ID - 1102 T2 - Proceedings of the British Machine Vision Conference 2016 TI - Improving weakly-supervised object localization by micro-annotation VL - 2016-September ER - TY - CONF AB - 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. AU - Martius, Georg S AU - Hostettler, Raphael AU - Knoll, Alois AU - Der, Ralf ID - 1214 TI - Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm VL - 2016-November ER - TY - CONF AB - 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. AU - Kolesnikov, Alexander AU - Lampert, Christoph ID - 1369 TI - Seed, expand and constrain: Three principles for weakly-supervised image segmentation VL - 9908 ER - TY - CONF AB - 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. In 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. AU - Pielorz, Jasmin AU - Lampert, Christoph ID - 1707 TI - Optimal geospatial allocation of volunteers for crisis management ER - TY - CONF AB - 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. AU - Martius, Georg S AU - Hostettler, Rafael AU - Knoll, Alois AU - Der, Ralf ID - 8094 SN - 9780262339360 T2 - Proceedings of the Artificial Life Conference 2016 TI - Self-organized control of an tendon driven arm by differential extrinsic plasticity VL - 28 ER - TY - THES AB - Traditionally machine learning has been focusing on the problem of solving a single task in isolation. While being quite well understood, this approach disregards an important aspect of human learning: when facing a new problem, humans are able to exploit knowledge acquired from previously learned tasks. Intuitively, access to several problems simultaneously or sequentially could also be advantageous for a machine learning system, especially if these tasks are closely related. Indeed, results of many empirical studies have provided justification for this intuition. However, theoretical justifications of this idea are rather limited. The focus of this thesis is to expand the understanding of potential benefits of information transfer between several related learning problems. We provide theoretical analysis for three scenarios of multi-task learning - multiple kernel learning, sequential learning and active task selection. We also provide a PAC-Bayesian perspective on lifelong learning and investigate how the task generation process influences the generalization guarantees in this scenario. In addition, we show how some of the obtained theoretical results can be used to derive principled multi-task and lifelong learning algorithms and illustrate their performance on various synthetic and real-world datasets. AU - Pentina, Anastasia ID - 1126 SN - 2663-337X TI - Theoretical foundations of multi-task lifelong learning ER - TY - CONF AB - 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. AU - Pentina, Anastasia AU - Lampert, Christoph ID - 1425 TI - Lifelong learning with non-i.i.d. tasks VL - 2015 ER - TY - JOUR AB - 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. AU - Xia, Wei AU - Domokos, Csaba AU - Xiong, Junjun AU - Cheong, Loongfah AU - Yan, Shuicheng ID - 1533 IS - 8 JF - IEEE Transactions on Circuits and Systems for Video Technology TI - Segmentation over detection via optimal sparse reconstructions VL - 25 ER - TY - JOUR AB - 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. AU - Der, Ralf AU - Martius, Georg S ID - 1570 IS - 45 JF - PNAS TI - Novel plasticity rule can explain the development of sensorimotor intelligence VL - 112 ER -