TY - JOUR AU - Morandell, Jasmin AU - Nicolas, Armel AU - Schwarz, Lena A AU - Novarino, Gaia ID - 7415 IS - Supplement 6 JF - European Neuropsychopharmacology SN - 0924-977X TI - S.16.05 Illuminating the role of the e3 ubiquitin ligase cullin3 in brain development and autism VL - 29 ER - TY - JOUR AU - Knaus, Lisa AU - Tarlungeanu, Dora-Clara AU - Novarino, Gaia ID - 7414 IS - Supplement 6 JF - European Neuropsychopharmacology SN - 0924-977X TI - S.16.03 A homozygous missense mutation in SLC7A5 leads to autism spectrum disorder and microcephaly VL - 29 ER - TY - JOUR AU - Benková, Eva AU - Dagdas, Yasin ID - 7394 IS - 12 JF - Current Opinion in Plant Biology SN - 1369-5266 TI - Editorial overview: Cell biology in the era of omics? VL - 52 ER - TY - CONF AB - Multi-exit architectures, in which a stack of processing layers is interleaved with early output layers, allow the processing of a test example to stop early and thus save computation time and/or energy. In this work, we propose a new training procedure for multi-exit architectures based on the principle of knowledge distillation. The method encourage searly exits to mimic later, more accurate exits, by matching their output probabilities. Experiments on CIFAR100 and ImageNet show that distillation-based training significantly improves the accuracy of early exits while maintaining state-of-the-art accuracy for late ones. The method is particularly beneficial when training data is limited and it allows a straightforward extension to semi-supervised learning,i.e. making use of unlabeled data at training time. Moreover, it takes only afew lines to implement and incurs almost no computational overhead at training time, and none at all at test time. AU - Bui Thi Mai, Phuong AU - Lampert, Christoph ID - 7479 SN - 15505499 T2 - IEEE International Conference on Computer Vision TI - Distillation-based training for multi-exit architectures VL - 2019-October ER - TY - CONF AB - We present a novel class of convolutional neural networks (CNNs) for set functions,i.e., data indexed with the powerset of a finite set. The convolutions are derivedas linear, shift-equivariant functions for various notions of shifts on set functions.The framework is fundamentally different from graph convolutions based on theLaplacian, as it provides not one but several basic shifts, one for each element inthe ground set. Prototypical experiments with several set function classificationtasks on synthetic datasets and on datasets derived from real-world hypergraphsdemonstrate the potential of our new powerset CNNs. AU - Wendler, Chris AU - Alistarh, Dan-Adrian AU - Püschel, Markus ID - 7542 SN - 1049-5258 TI - Powerset convolutional neural networks VL - 32 ER - TY - CHAP AB - Social insects (i.e., ants, termites and the social bees and wasps) protect their colonies from disease using a combination of individual immunity and collectively performed defenses, termed social immunity. The first line of social immune defense is sanitary care, which is performed by colony members to protect their pathogen-exposed nestmates from developing an infection. If sanitary care fails and an infection becomes established, a second line of social immune defense is deployed to stop disease transmission within the colony and to protect the valuable queens, which together with the males are the reproductive individuals of the colony. Insect colonies are separated into these reproductive individuals and the sterile worker force, forming a superorganismal reproductive unit reminiscent of the differentiated germline and soma in a multicellular organism. Ultimately, the social immune response preserves the germline of the superorganism insect colony and increases overall fitness of the colony in case of disease. AU - Cremer, Sylvia AU - Kutzer, Megan ED - Choe, Jae ID - 7513 SN - 9780128132517 T2 - Encyclopedia of Animal Behavior TI - Social immunity ER - TY - CONF AB - Bending-active structures are able to efficiently produce complex curved shapes starting from flat panels. The desired deformation of the panels derives from the proper selection of their elastic properties. Optimized panels, called FlexMaps, are designed such that, once they are bent and assembled, the resulting static equilibrium configuration matches a desired input 3D shape. The FlexMaps elastic properties are controlled by locally varying spiraling geometric mesostructures, which are optimized in size and shape to match the global curvature (i.e., bending requests) of the target shape. The design pipeline starts from a quad mesh representing the input 3D shape, which defines the edge size and the total amount of spirals: every quad will embed one spiral. Then, an optimization algorithm tunes the geometry of the spirals by using a simplified pre-computed rod model. This rod model is derived from a non-linear regression algorithm which approximates the non-linear behavior of solid FEM spiral models subject to hundreds of load combinations. This innovative pipeline has been applied to the project of a lightweight plywood pavilion named FlexMaps Pavilion, which is a single-layer piecewise twisted arc that fits a bounding box of 3.90x3.96x3.25 meters. AU - Laccone, Francesco AU - Malomo, Luigi AU - Perez Rodriguez, Jesus AU - Pietroni, Nico AU - Ponchio, Federico AU - Bickel, Bernd AU - Cignoni, Paolo ID - 9261 SN - 2518-6582 T2 - IASS Symposium 2019 - 60th Anniversary Symposium of the International Association for Shell and Spatial Structures; Structural Membranes 2019 - 9th International Conference on Textile Composites and Inflatable Structures, FORM and FORCE TI - FlexMaps Pavilion: A twisted arc made of mesostructured flat flexible panels ER - TY - CONF AB - We propose a new model for detecting visual relationships, such as "person riding motorcycle" or "bottle on table". This task is an important step towards comprehensive structured mage understanding, going beyond detecting individual objects. Our main novelty is a Box Attention mechanism that allows to model pairwise interactions between objects using standard object detection pipelines. The resulting model is conceptually clean, expressive and relies on well-justified training and prediction procedures. Moreover, unlike previously proposed approaches, our model does not introduce any additional complex components or hyperparameters on top of those already required by the underlying detection model. We conduct an experimental evaluation on two datasets, V-COCO and Open Images, demonstrating strong quantitative and qualitative results. AU - Kolesnikov, Alexander AU - Kuznetsova, Alina AU - Lampert, Christoph AU - Ferrari, Vittorio ID - 7640 SN - 9781728150239 T2 - Proceedings of the 2019 International Conference on Computer Vision Workshop TI - Detecting visual relationships using box attention ER - TY - CONF AB - Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achieved by indirect means, largely due to the complex set of functions defined by a network and the difficulty in measuring function complexity. There exists no method in the literature for additive regularization based on a norm of the function, as is classically considered in statistical learning theory. In this work, we study the tractability of function norms for deep neural networks with ReLU activations. We provide, to the best of our knowledge, the first proof in the literature of the NP-hardness of computing function norms of DNNs of 3 or more layers. We also highlight a fundamental difference between shallow and deep networks. In the light on these results, we propose a new regularization strategy based on approximate function norms, and show its efficiency on a segmentation task with a DNN. AU - Rannen-Triki, Amal AU - Berman, Maxim AU - Kolmogorov, Vladimir AU - Blaschko, Matthew B. ID - 7639 SN - 9781728150239 T2 - Proceedings of the 2019 International Conference on Computer Vision Workshop TI - Function norms for neural networks ER - TY - CHAP AB - We review the history of population genetics, starting with its origins a century ago from the synthesis between Mendel and Darwin's ideas, through to the recent development of sophisticated schemes of inference from sequence data, based on the coalescent. We explain the close relation between the coalescent and a diffusion process, which we illustrate by their application to understand spatial structure. We summarise the powerful methods available for analysis of multiple loci, when linkage equilibrium can be assumed, and then discuss approaches to the more challenging case, where associations between alleles require that we follow genotype, rather than allele, frequencies. Though we can hardly cover the whole of population genetics, we give an overview of the current state of the subject, and future challenges to it. AU - Barton, Nicholas H AU - Etheridge, Alison ED - Balding, David ED - Moltke, Ida ED - Marioni, John ID - 8281 SN - 9781119429142 T2 - Handbook of statistical genomics TI - Mathematical models in population genetics ER -