Institute Homepage
Institute Homepage EN Sign In

Publications

DEPARTMENTS

Emperical Interference

Haptic Intelligence

Modern Magnetic Systems

Perceiving Systems

Physical Intelligence

Robotic Materials

Social Foundations of Computation

Research Groups

Autonomous Vision

Autonomous Learning

Bioinspired Autonomous Miniature Robots

Dynamic Locomotion

Embodied Vision

Human Aspects of Machine Learning

Intelligent Control Systems

Learning and Dynamical Systems

Locomotion in Biorobotic and Somatic Systems

Micro, Nano, and Molecular Systems

Movement Generation and Control

Neural Capture and Synthesis

Physics for Inference and Optimization

Organizational Leadership and Diversity

Probabilistic Learning Group

Topics

Robot Learning

Conference Paper

2022

Autonomous Learning

Robotics

AI

Career

Award

Empirical Inference Conference Paper Adaptive Coding of Actions and Observations Ortega, P., Braun, D. 1-4, NIPS 2012 Workshop on Information in Perception and Action, December 2012
The application of expected utility theory to construct adaptive agents is both computationally intractable and statistically questionable. To overcome these difficulties, agents need the ability to delay the choice of the optimal policy to a later stage when they have learned more about the environment. How should agents do this optimally? An information-theoretic answer to this question is given by the Bayesian control rule—the solution to the adaptive coding problem when there are not only observations but also actions. This paper reviews the central ideas behind the Bayesian control rule.
URL BibTeX
Physical Intelligence Miscellaneous Dry adhesive structures Sitti, M., Murphy, M., Aksak, B. December 2012, US Patent App. 13/533,386 BibTeX
Empirical Inference Talk Hilbert Space Embedding for Dirichlet Process Mixtures Muandet, K. NIPS 2012 Workshop on Confluence between Kernel Methods and Graphical Models, December 2012 BibTeX
Empirical Inference Article Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices Cherian, A., Sra, S., Banerjee, A., Papanikolopoulos, N. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(9):2161-2174, December 2012 (Published) DOI BibTeX
Physical Intelligence Miscellaneous Methods, apparatuses, and systems for micromanipulation with adhesive fibrillar structures Sitti, M., Mengüç, Y. December 2012, US Patent App. 14/368,079 BibTeX
Empirical Inference Talk Support Vector Machines, Support Measure Machines, and Quasar Target Selection Muandet, K. Center for Cosmology and Particle Physics (CCPP), New York University, December 2012 BibTeX
Perceiving Systems Ph.D. Thesis Virtual Human Bodies with Clothing and Hair: From Images to Animation Guan, P. Brown University, Department of Computer Science, December 2012 BibTeX
Empirical Inference Article Hippocampal-Cortical Interaction during Periods of Subcortical Silence Logothetis, N., Eschenko, O., Murayama, Y., Augath, M., Steudel, T., Evrard, H., Besserve, M., Oeltermann, A. Nature, 491:547-553, November 2012
Hippocampal ripples, episodic high-frequency field-potential oscillations primarily occurring during sleep and calmness, have been described in mice, rats, rabbits, monkeys and humans, and so far they have been associated with retention of previously acquired awake experience. Although hippocampal ripples have been studied in detail using neurophysiological methods, the global effects of ripples on the entire brain remain elusive, primarily owing to a lack of methodologies permitting concurrent hippocampal recordings and whole-brain activity mapping. By combining electrophysiological recordings in hippocampus with ripple-triggered functional magnetic resonance imaging, here we show that most of the cerebral cortex is selectively activated during the ripples, whereas most diencephalic, midbrain and brainstem regions are strongly and consistently inhibited. Analysis of regional temporal response patterns indicates that thalamic activity suppression precedes the hippocampal population burst, which itself is temporally bounded by massive activations of association and primary cortical areas. These findings suggest that during off-line memory consolidation, synergistic thalamocortical activity may be orchestrating a privileged interaction state between hippocampus and cortex by silencing the output of subcortical centres involved in sensory processing or potentially mediating procedural learning. Such a mechanism would cause minimal interference, enabling consolidation of hippocampus-dependent memory.
Web DOI BibTeX
Movement Generation and Control Autonomous Motion Conference Paper Encoding of Periodic and their Transient Motions by a Single Dynamic Movement Primitive Ernesti, J., Righetti, L., Do, M., Asfour, T., Schaal, S. In 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012), 57-64, IEEE, Osaka, Japan, November 2012 DOI URL BibTeX
Movement Generation and Control Autonomous Motion Conference Paper Quadratic programming for inverse dynamics with optimal distribution of contact forces Righetti, L., Schaal, S. In 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012), 538-543, IEEE, Osaka, Japan, November 2012
In this contribution we propose an inverse dynamics controller for a humanoid robot that exploits torque redundancy to minimize any combination of linear and quadratic costs in the contact forces and the commands. In addition the controller satisfies linear equality and inequality constraints in the contact forces and the commands such as torque limits, unilateral contacts or friction cones limits. The originality of our approach resides in the formulation of the problem as a quadratic program where we only need to solve for the control commands and where the contact forces are optimized implicitly. Furthermore, we do not need a structured representation of the dynamics of the robot (i.e. an explicit computation of the inertia matrix). It is in contrast with existing methods based on quadratic programs. The controller is then robust to uncertainty in the estimation of the dynamics model and the optimization is fast enough to be implemented in high bandwidth torque control loops that are increasingly available on humanoid platforms. We demonstrate properties of our controller with simulations of a human size humanoid robot.
DOI URL BibTeX
Movement Generation and Control Autonomous Motion Conference Paper Towards Associative Skill Memories Pastor, P., Kalakrishnan, M., Righetti, L., Schaal, S. In 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012), 309-315, IEEE, Osaka, Japan, November 2012
Movement primitives as basis of movement planning and control have become a popular topic in recent years. The key idea of movement primitives is that a rather small set of stereotypical movements should suffice to create a large set of complex manipulation skills. An interesting side effect of stereotypical movement is that it also creates stereotypical sensory events, e.g., in terms of kinesthetic variables, haptic variables, or, if processed appropriately, visual variables. Thus, a movement primitive executed towards a particular object in the environment will associate a large number of sensory variables that are typical for this manipulation skill. These association can be used to increase robustness towards perturbations, and they also allow failure detection and switching towards other behaviors. We call such movement primitives augmented with sensory associations Associative Skill Memories (ASM). This paper addresses how ASMs can be acquired by imitation learning and how they can create robust manipulation skill by determining subsequent ASMs online to achieve a particular manipulation goal. Evaluation for grasping and manipulation with a Barrett WAM/Hand illustrate our approach.
DOI URL BibTeX
Empirical Inference Ph.D. Thesis Scalable graph kernels Shervashidze, N. Eberhard Karls Universität Tübingen, Germany, October 2012 Web BibTeX
Perceiving Systems Conference Paper 3D2PM – 3D Deformable Part Models Pepik, B., Gehler, P., Stark, M., Schiele, B. In Proceedings of the European Conference on Computer Vision (ECCV), 356-370, Lecture Notes in Computer Science, (Editors: Fitzgibbon, Andrew W. and Lazebnik, Svetlana and Perona, Pietro and Sato, Yoichi and Schmid, Cordelia), Springer, Firenze, October 2012 pdf video poster BibTeX
Perceiving Systems Conference Paper A naturalistic open source movie for optical flow evaluation Butler, D. J., Wulff, J., Stanley, G. B., Black, M. J. In European Conf. on Computer Vision (ECCV), 611-625, Part IV, LNCS 7577, (Editors: A. Fitzgibbon et al. (Eds.)), Springer-Verlag, October 2012
Ground truth optical flow is difficult to measure in real scenes with natural motion. As a result, optical flow data sets are restricted in terms of size, complexity, and diversity, making optical flow algorithms difficult to train and test on realistic data. We introduce a new optical flow data set derived from the open source 3D animated short film Sintel. This data set has important features not present in the popular Middlebury flow evaluation: long sequences, large motions, specular reflections, motion blur, defocus blur, and atmospheric effects. Because the graphics data that generated the movie is open source, we are able to render scenes under conditions of varying complexity to evaluate where existing flow algorithms fail. We evaluate several recent optical flow algorithms and find that current highly-ranked methods on the Middlebury evaluation have difficulty with this more complex data set suggesting further research on optical flow estimation is needed. To validate the use of synthetic data, we compare the image- and flow-statistics of Sintel to those of real films and videos and show that they are similar. The data set, metrics, and evaluation website are publicly available.
pdf dataset youtube talk supplemental material BibTeX
Empirical Inference Article A sensorimotor paradigm for Bayesian model selection Genewein, T., Braun, D. Frontiers in Human Neuroscience, 6(291):1-16, October 2012
Sensorimotor control is thought to rely on predictive internal models in order to cope efficiently with uncertain environments. Recently, it has been shown that humans not only learn different internal models for different tasks, but that they also extract common structure between tasks. This raises the question of how the motor system selects between different structures or models, when each model can be associated with a range of different task-specific parameters. Here we design a sensorimotor task that requires subjects to compensate visuomotor shifts in a three-dimensional virtual reality setup, where one of the dimensions can be mapped to a model variable and the other dimension to the parameter variable. By introducing probe trials that are neutral in the parameter dimension, we can directly test for model selection. We found that model selection procedures based on Bayesian statistics provided a better explanation for subjects’ choice behavior than simple non-probabilistic heuristics. Our experimental design lends itself to the general study of model selection in a sensorimotor context as it allows to separately query model and parameter variables from subjects.
DOI BibTeX
Perceiving Systems Conference Paper Coregistration: Simultaneous alignment and modeling of articulated 3D shape Hirshberg, D., Loper, M., Rachlin, E., Black, M. In European Conf. on Computer Vision (ECCV), 242-255, LNCS 7577, Part IV, (Editors: A. Fitzgibbon et al. (Eds.)), Springer-Verlag, October 2012
Three-dimensional (3D) shape models are powerful because they enable the inference of object shape from incomplete, noisy, or ambiguous 2D or 3D data. For example, realistic parameterized 3D human body models have been used to infer the shape and pose of people from images. To train such models, a corpus of 3D body scans is typically brought into registration by aligning a common 3D human-shaped template to each scan. This is an ill-posed problem that typically involves solving an optimization problem with regularization terms that penalize implausible deformations of the template. When aligning a corpus, however, we can do better than generic regularization. If we have a model of how the template can deform then alignments can be regularized by this model. Constructing a model of deformations, however, requires having a corpus that is already registered. We address this chicken-and-egg problem by approaching modeling and registration together. By minimizing a single objective function, we reliably obtain high quality registration of noisy, incomplete, laser scans, while simultaneously learning a highly realistic articulated body model. The model greatly improves robustness to noise and missing data. Since the model explains a corpus of body scans, it captures how body shape varies across people and poses.
pdf publisher site poster supplemental material (400MB) DOI BibTeX
Perceiving Systems Technical Report Coregistration: Supplemental Material Hirshberg, D., Loper, M., Rachlin, E., Black, M. J. (No. 4), Max Planck Institute for Intelligent Systems, October 2012 pdf BibTeX
Perceiving Systems Article Coupled Action Recognition and Pose Estimation from Multiple Views Yao, A., Gall, J., van Gool, L. International Journal of Computer Vision, 100(1):16-37, October 2012 publisher's site code pdf BibTeX
Autonomous Motion Conference Paper Failure Recovery with Shared Autonomy Sankaran, B., Pitzer, B., Osentoski, S. In International Conference on Intelligent Robots and Systems, October 2012 (Published)
Building robots capable of long term autonomy has been a long standing goal of robotics research. Such systems must be capable of performing certain tasks with a high degree of robustness and repeatability. In the context of personal robotics, these tasks could range anywhere from retrieving items from a refrigerator, loading a dishwasher, to setting up a dinner table. Given the complexity of tasks there are a multitude of failure scenarios that the robot can encounter, irrespective of whether the environment is static or dynamic. For a robot to be successful in such situations, it would need to know how to recover from failures or when to ask a human for help. This paper, presents a novel shared autonomy behavioral executive to addresses these issues. We demonstrate how this executive combines generalized logic based recovery and human intervention to achieve continuous failure free operation. We tested the systems over 250 trials of two different use case experiments. Our current algorithm drastically reduced human intervention from 26% to 4% on the first experiment and 46% to 9% on the second experiment. This system provides a new dimension to robot autonomy, where robots can exhibit long term failure free operation with minimal human supervision. We also discuss how the system can be generalized.
URL BibTeX
Perceiving Systems Conference Paper Lessons and insights from creating a synthetic optical flow benchmark Wulff, J., Butler, D. J., Stanley, G. B., Black, M. J. In ECCV Workshop on Unsolved Problems in Optical Flow and Stereo Estimation, 168-177, Part II, LNCS 7584, (Editors: A. Fusiello et al. (Eds.)), Springer-Verlag, October 2012 pdf dataset poster youtube BibTeX
Perceiving Systems Conference Paper Lie Bodies: A Manifold Representation of 3D Human Shape Freifeld, O., Black, M. J. In European Conf. on Computer Vision (ECCV), 1-14, Part I, LNCS 7572, (Editors: A. Fitzgibbon et al. (Eds.)), Springer-Verlag, October 2012
Three-dimensional object shape is commonly represented in terms of deformations of a triangular mesh from an exemplar shape. Existing models, however, are based on a Euclidean representation of shape deformations. In contrast, we argue that shape has a manifold structure: For example, summing the shape deformations for two people does not necessarily yield a deformation corresponding to a valid human shape, nor does the Euclidean difference of these two deformations provide a meaningful measure of shape dissimilarity. Consequently, we define a novel manifold for shape representation, with emphasis on body shapes, using a new Lie group of deformations. This has several advantages. First we define triangle deformations exactly, removing non-physical deformations and redundant degrees of freedom common to previous methods. Second, the Riemannian structure of Lie Bodies enables a more meaningful definition of body shape similarity by measuring distance between bodies on the manifold of body shape deformations. Third, the group structure allows the valid composition of deformations. This is important for models that factor body shape deformations into multiple causes or represent shape as a linear combination of basis shapes. Finally, body shape variation is modeled using statistics on manifolds. Instead of modeling Euclidean shape variation with Principal Component Analysis we capture shape variation on the manifold using Principal Geodesic Analysis. Our experiments show consistent visual and quantitative advantages of Lie Bodies over traditional Euclidean models of shape deformation and our representation can be easily incorporated into existing methods.
pdf supplemental material youtube poster eigenshape video code BibTeX
Perceiving Systems Technical Report Lie Bodies: A Manifold Representation of 3D Human Shape. Supplemental Material Freifeld, O., Black, M. J. (No. 5), Max Planck Institute for Intelligent Systems, October 2012 pdf BibTeX
Perceiving Systems Technical Report MPI-Sintel Optical Flow Benchmark: Supplemental Material Butler, D. J., Wulff, J., Stanley, G. B., Black, M. J. (No. 6), Max Planck Institute for Intelligent Systems, October 2012 pdf BibTeX
Empirical Inference Article Thermodynamic limits of dynamic cooling Allahverdyan, A., Hovhannisyan, K., Janzing, D., Mahler, G. Physical Review E, 84(4):16, October 2012
We study dynamic cooling, where an externally driven two-level system is cooled via reservoir, a quantum system with initial canonical equilibrium state. We obtain explicitly the minimal possible temperature Tmin>0 reachable for the two-level system. The minimization goes over all unitary dynamic processes operating on the system and reservoir and over the reservoir energy spectrum. The minimal work needed to reach Tmin grows as 1/Tmin. This work cost can be significantly reduced, though, if one is satisfied by temperatures slightly above Tmin. Our results on Tmin>0 prove unattainability of the absolute zero temperature without ambiguities that surround its derivation from the entropic version of the third law. We also study cooling via a reservoir consisting of N≫1 identical spins. Here we show that Tmin∝1/N and find the maximal cooling compatible with the minimal work determined by the free energy. Finally we discuss cooling by reservoir with an initially microcanonic state and show that although a purely microcanonic state can yield the zero temperature, the unattainability is recovered when taking into account imperfections in preparing the microcanonic state.
Web DOI BibTeX
Autonomous Motion Conference Paper Towards Multi-DOF model mediated teleoperation: Using vision to augment feedback Willaert, B., Bohg, J., Van Brussel, H., Niemeyer, G. In IEEE International Workshop on Haptic Audio Visual Environments and Games (HAVE), 25-31, October 2012
In this paper, we address some of the challenges that arise as model-mediated teleoperation is applied to systems with multiple degrees of freedom and multiple sensors. Specifically we use a system with position, force, and vision sensors to explore an environment geometry in two degrees of freedom. The inclusion of vision is proposed to alleviate the difficulties of estimating an increasing number of environment properties. Vision can furthermore increase the predictive nature of model-mediated teleoperation, by effectively predicting touch feedback before the slave is even in contact with the environment. We focus on the case of estimating the location and orientation of a local surface patch at the contact point between the slave and the environment. We describe the various information sources with their respective limitations and create a combined model estimator as part of a multi-d.o.f. model-mediated controller. An experiment demonstrates the feasibility and benefits of utilizing vision sensors in teleoperation.
DOI BibTeX
Empirical Inference Article GLIDE: GPU-Based Linear Regression for Detection of Epistasis Kam-Thong, T., Azencott, C., Cayton, L., Pütz, B., Altmann, A., Karbalai, N., Sämann, P., Schölkopf, B., Müller-Myhsok, B., Borgwardt, K. Human Heredity, 73(4):220-236, September 2012
Due to recent advances in genotyping technologies, mapping phenotypes to single loci in the genome has become a standard technique in statistical genetics. However, one-locus mapping fails to explain much of the phenotypic variance in complex traits. Here, we present GLIDE, which maps phenotypes to pairs of genetic loci and systematically searches for the epistatic interactions expected to reveal part of this missing heritability. GLIDE makes use of the computational power of consumer-grade graphics cards to detect such interactions via linear regression. This enabled us to conduct a systematic two-locus mapping study on seven disease data sets from the Wellcome Trust Case Control Consortium and on in-house hippocampal volume data in 6 h per data set, while current single CPU-based approaches require more than a year’s time to complete the same task.
Web BibTeX
Empirical Inference Article Bayesian estimation of free energies from equilibrium simulations Habeck, M. Physical Review Letters, 109(10):5, September 2012
Free energy calculations are an important tool in statistical physics and biomolecular simulation. This Letter outlines a Bayesian method to estimate free energies from equilibrium Monte Carlo simulations. A Gibbs sampler is developed that allows efficient sampling of free energies and the density of states. The Gibbs sampling output can be used to estimate expected free energy differences and their uncertainties. The probabilistic formulation offers a unifying framework for existing methods such as the weighted histogram analysis method and the multistate Bennett acceptance ratio; both are shown to be approximate versions of the full probabilistic treatment.
Web DOI BibTeX
Empirical Inference Article Fast projection onto mixed-norm balls with applications Sra, S. Minining and Knowledge Discovery (DMKD), 25(2):358-377, September 2012 (Published) DOI BibTeX
Empirical Inference Article Risk-Sensitivity in Bayesian Sensorimotor Integration Grau-Moya, J., Ortega, P., Braun, D. PLoS Computational Biology, 8(9):1-7, September 2012
Information processing in the nervous system during sensorimotor tasks with inherent uncertainty has been shown to be consistent with Bayesian integration. Bayes optimal decision-makers are, however, risk-neutral in the sense that they weigh all possibilities based on prior expectation and sensory evidence when they choose the action with highest expected value. In contrast, risk-sensitive decision-makers are sensitive to model uncertainty and bias their decision-making processes when they do inference over unobserved variables. In particular, they allow deviations from their probabilistic model in cases where this model makes imprecise predictions. Here we test for risk-sensitivity in a sensorimotor integration task where subjects exhibit Bayesian information integration when they infer the position of a target from noisy sensory feedback. When introducing a cost associated with subjects' response, we found that subjects exhibited a characteristic bias towards low cost responses when their uncertainty was high. This result is in accordance with risk-sensitive decision-making processes that allow for deviations from Bayes optimal decision-making in the face of uncertainty. Our results suggest that both Bayesian integration and risk-sensitivity are important factors to understand sensorimotor integration in a quantitative fashion.
DOI BibTeX
Autonomous Motion Conference Paper Task-Based Grasp Adaptation on a Humanoid Robot Bohg, J., Welke, K., León, B., Do, M., Song, D., Wohlkinger, W., Aldoma, A., Madry, M., Przybylski, M., Asfour, T., Marti, H., Kragic, D., Morales, A., Vincze, M. In 10th IFAC Symposium on Robot Control, SyRoCo 2012, Dubrovnik, Croatia, September 5-7, 2012., 779-786, September 2012
In this paper, we present an approach towards autonomous grasping of objects according to their category and a given task. Recent advances in the field of object segmentation and categorization as well as task-based grasp inference have been leveraged by integrating them into one pipeline. This allows us to transfer task-specific grasp experience between objects of the same category. The effectiveness of the approach is demonstrated on the humanoid robot ARMAR-IIIa.
Video pdf DOI BibTeX
Perceiving Systems Conference Paper A framework for relating neural activity to freely moving behavior Foster, J. D., Nuyujukian, P., Freifeld, O., Ryu, S., Black, M. J., Shenoy, K. V. In 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’12), 2736 -2739 , IEEE, San Diego, August 2012 pdf BibTeX
Perceiving Systems Conference Paper Pottics – The Potts Topic Model for Semantic Image Segmentation Dann, C., Gehler, P., Roth, S., Nowozin, S. In Proceedings of 34th DAGM Symposium, 397-407, Lecture Notes in Computer Science, (Editors: Pinz, Axel and Pock, Thomas and Bischof, Horst and Leberl, Franz), Springer, August 2012 code pdf poster BibTeX
Autonomous Motion Conference Paper An adaptive sensor foot for a bipedal and quadrupedal robot Fondahl, K., Kuehn, D., Beinersdorf, F., Bernhard, F., Grimminger, F., Schilling, M., Stark, T., Kirchner, F. In 2012 4th IEEE RAS EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob), 270-275, July 2012 DOI BibTeX
Empirical Inference Conference Paper Free Energy and the Generalized Optimality Equations for Sequential Decision Making Ortega, P., Braun, D. 1-10, 10th European Workshop on Reinforcement Learning (EWRL 2012), July 2012
The free energy functional has recently been proposed as a variational principle for bounded rational decision-making, since it instantiates a natural trade-off between utility gains and information processing costs that can be axiomatically derived. Here we apply the free energy principle to general decision trees that include both adversarial and stochastic environments. We derive generalized sequential optimality equations that not only include the Bellman optimality equations as a limit case, but also lead to well-known decision-rules such as Expectimax, Minimax and Expectiminimax. We show how these decision-rules can be derived from a single free energy principle that assigns a resource parameter to each node in the decision tree. These resource parameters express a concrete computational cost that can be measured as the amount of samples that are needed from the distribution that belongs to each node. The free energy principle therefore provides the normative basis for generalized optimality equations that account for both adversarial and stochastic environments.
URL BibTeX
Perceiving Systems Ph.D. Thesis From Pixels to Layers: Joint Motion Estimation and Segmentation Sun, D. Brown University, Department of Computer Science, July 2012 pdf BibTeX
Empirical Inference Conference Paper Influence Maximization in Continuous Time Diffusion Networks Gomez Rodriguez, M., Schölkopf, B. In Proceedings of the 29th International Conference on Machine Learning, 313-320, (Editors: J, Langford and J, Pineau), Omnipress, New York, NY, USA, ICML, July 2012 Web BibTeX
Physical Intelligence Miscellaneous Methods of making dry adhesives Sitti, M., Murphy, M., Aksak, B. July 2012, US Patent 8,206,631 BibTeX
Perceiving Systems Empirical Inference Probabilistic Numerics Conference Paper Quasi-Newton Methods: A New Direction Hennig, P., Kiefel, M. In Proceedings of the 29th International Conference on Machine Learning, 25-32, ICML ’12, (Editors: John Langford and Joelle Pineau), Omnipress, New York, NY, USA, ICML, July 2012
Four decades after their invention, quasi- Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that fit a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newton methods can be interpreted as approximations of Bayesian linear regression under varying prior assumptions. This new notion elucidates some shortcomings of classical algorithms, and lights the way to a novel nonparametric quasi-Newton method, which is able to make more efficient use of available information at computational cost similar to its predecessors.
website+code pdf URL BibTeX
Empirical Inference Conference Paper Submodular Inference of Diffusion Networks from Multiple Trees Gomez Rodriguez, M., Schölkopf, B. In Proceedings of the 29th International Conference on Machine Learning , 489-496, (Editors: J Langford, and J Pineau), Omnipress, New York, NY, USA, ICML, July 2012 Web BibTeX
Perceiving Systems Article DRAPE: DRessing Any PErson Guan, P., Reiss, L., Hirshberg, D., Weiss, A., Black, M. J. ACM Trans. on Graphics (Proc. SIGGRAPH), 31(4):35:1-35:10, July 2012
We describe a complete system for animating realistic clothing on synthetic bodies of any shape and pose without manual intervention. The key component of the method is a model of clothing called DRAPE (DRessing Any PErson) that is learned from a physics-based simulation of clothing on bodies of different shapes and poses. The DRAPE model has the desirable property of "factoring" clothing deformations due to body shape from those due to pose variation. This factorization provides an approximation to the physical clothing deformation and greatly simplifies clothing synthesis. Given a parameterized model of the human body with known shape and pose parameters, we describe an algorithm that dresses the body with a garment that is customized to fit and possesses realistic wrinkles. DRAPE can be used to dress static bodies or animated sequences with a learned model of the cloth dynamics. Since the method is fully automated, it is appropriate for dressing large numbers of virtual characters of varying shape. The method is significantly more efficient than physical simulation.
YouTube pdf talk BibTeX
Empirical Inference Conference Paper Climate classifications: the value of unsupervised clustering Zscheischler, J., Mahecha, M., Harmeling, S. In Proceedings of the International Conference on Computational Science , 9:897-906, Procedia Computer Science, (Editors: H. Ali, Y. Shi, D. Khazanchi, M. Lees, G.D. van Albada, J. Dongarra, P.M.A. Sloot, J. Dongarra), Elsevier, Amsterdam, Netherlands, ICCS, June 2012
Classifying the land surface according to di erent climate zones is often a prerequisite for global diagnostic or predictive modelling studies. Classical classifications such as the prominent K¨oppen–Geiger (KG) approach rely on heuristic decision rules. Although these heuristics may transport some process understanding, such a discretization may appear “arbitrary” from a data oriented perspective. In this contribution we compare the precision of a KG classification to an unsupervised classification (k-means clustering). Generally speaking, we revisit the problem of “climate classification” by investigating the inherent patterns in multiple data streams in a purely data driven way. One question is whether we can reproduce the KG boundaries by exploring di erent combinations of climate and remotely sensed vegetation variables. In this context we also investigate whether climate and vegetation variables build similar clusters. In terms of statistical performances, k-means clearly outperforms classical climate classifications. However, a subsequent stability analysis only reveals a meaningful number of clusters if both climate and vegetation data are considered in the analysis. This is a setback for the hope to explain vegetation by means of climate alone. Clearly, classification schemes like K¨oppen-Geiger will play an important role in the future. However, future developments in this area need to be assessed based on data driven approaches.
Web DOI BibTeX
Empirical Inference Probabilistic Numerics Article Entropy Search for Information-Efficient Global Optimization Hennig, P., Schuler, C. Journal of Machine Learning Research, 13:1809-1837, -, June 2012
Contemporary global optimization algorithms are based on local measures of utility, rather than a probability measure over location and value of the optimum. They thus attempt to collect low function values, not to learn about the optimum. The reason for the absence of probabilistic global optimizers is that the corresponding inference problem is intractable in several ways. This paper develops desiderata for probabilistic optimization algorithms, then presents a concrete algorithm which addresses each of the computational intractabilities with a sequence of approximations and explicitly adresses the decision problem of maximizing information gain from each evaluation.
PDF Web BibTeX
Perceiving Systems Conference Paper From pictorial structures to deformable structures Zuffi, S., Freifeld, O., Black, M. J. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 3546-3553, IEEE, June 2012
Pictorial Structures (PS) define a probabilistic model of 2D articulated objects in images. Typical PS models assume an object can be represented by a set of rigid parts connected with pairwise constraints that define the prior probability of part configurations. These models are widely used to represent non-rigid articulated objects such as humans and animals despite the fact that such objects have parts that deform non-rigidly. Here we define a new Deformable Structures (DS) model that is a natural extension of previous PS models and that captures the non-rigid shape deformation of the parts. Each part in a DS model is represented by a low-dimensional shape deformation space and pairwise potentials between parts capture how the shape varies with pose and the shape of neighboring parts. A key advantage of such a model is that it more accurately models object boundaries. This enables image likelihood models that are more discriminative than previous PS likelihoods. This likelihood is learned using training imagery annotated using a DS “puppet.” We focus on a human DS model learned from 2D projections of a realistic 3D human body model and use it to infer human poses in images using a form of non-parametric belief propagation.
pdf sup mat code poster BibTeX
Empirical Inference Conference Paper Image denoising: Can plain Neural Networks compete with BM3D? Burger, H., Schuler, C., Harmeling, S. In 2392 - 2399, 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012), June 2012
Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. The best currently available denoising methods approximate this mapping with cleverly engineered algorithms. In this work we attempt to learn this mapping directly with a plain multi layer perceptron (MLP) applied to image patches. While this has been done before, we will show that by training on large image databases we are able to compete with the current state-of-the-art image denoising methods. Furthermore, our approach is easily adapted to less extensively studied types of noise (by merely exchanging the training data), for which we achieve excellent results as well.
PDF Web DOI BibTeX
Empirical Inference Article PAC-Bayesian Inequalities for Martingales Seldin, Y., Laviolette, F., Cesa-Bianchi, N., Shawe-Taylor, J., Auer, P. IEEE Transactions on Information Theory, 58(12):7086-7093, June 2012 (Published)
We present a set of high-probability inequalities that control the concentration of weighted averages of multiple (possibly uncountably many) simultaneously evolving and interdependent martingales. We also present a comparison inequality that bounds expectation of a convex function of martingale difference type variables by expectation of the same function of independent Bernoulli variables. This inequality is applied to derive a tighter analog of Hoeffding-Azuma inequality.
PDF Web DOI BibTeX
Perceiving Systems Conference Paper Teaching 3D Geometry to Deformable Part Models Pepik, B., Stark, M., Gehler, P., Schiele, B. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3362 -3369, IEEE, Providence, RI, USA, June 2012, oral presentation pdf DOI BibTeX
Perceiving Systems Article Visual Orientation and Directional Selectivity Through Thalamic Synchrony Stanley, G., Jin, J., Wang, Y., Desbordes, G., Wang, Q., Black, M., Alonso, J. Journal of Neuroscience, 32(26):9073-9088, June 2012
Thalamic neurons respond to visual scenes by generating synchronous spike trains on the timescale of 10–20 ms that are very effective at driving cortical targets. Here we demonstrate that this synchronous activity contains unexpectedly rich information about fundamental properties of visual stimuli. We report that the occurrence of synchronous firing of cat thalamic cells with highly overlapping receptive fields is strongly sensitive to the orientation and the direction of motion of the visual stimulus. We show that this stimulus selectivity is robust, remaining relatively unchanged under different contrasts and temporal frequencies (stimulus velocities). A computational analysis based on an integrate-and-fire model of the direct thalamic input to a layer 4 cortical cell reveals a strong correlation between the degree of thalamic synchrony and the nonlinear relationship between cortical membrane potential and the resultant firing rate. Together, these findings suggest a novel population code in the synchronous firing of neurons in the early visual pathway that could serve as the substrate for establishing cortical representations of the visual scene.
preprint BibTeX
Empirical Inference Article A Neuromorphic Architecture for Object Recognition and Motion Anticipation Using Burst-STDP Nere, A., Olcese, U., Balduzzi, D., Tononi, G. PLoS ONE, 7(5):17, May 2012
In this work we investigate the possibilities offered by a minimal framework of artificial spiking neurons to be deployed in silico. Here we introduce a hierarchical network architecture of spiking neurons which learns to recognize moving objects in a visual environment and determine the correct motor output for each object. These tasks are learned through both supervised and unsupervised spike timing dependent plasticity (STDP). STDP is responsible for the strengthening (or weakening) of synapses in relation to pre- and post-synaptic spike times and has been described as a Hebbian paradigm taking place both in vitro and in vivo. We utilize a variation of STDP learning, called burst-STDP, which is based on the notion that, since spikes are expensive in terms of energy consumption, then strong bursting activity carries more information than single (sparse) spikes. Furthermore, this learning algorithm takes advantage of homeostatic renormalization, which has been hypothesized to promote memory consolidation during NREM sleep. Using this learning rule, we design a spiking neural network architecture capable of object recognition, motion detection, attention towards important objects, and motor control outputs. We demonstrate the abilities of our design in a simple environment with distractor objects, multiple objects moving concurrently, and in the presence of noise. Most importantly, we show how this neural network is capable of performing these tasks using a simple leaky-integrate-and-fire (LIF) neuron model with binary synapses, making it fully compatible with state-of-the-art digital neuromorphic hardware designs. As such, the building blocks and learning rules presented in this paper appear promising for scalable fully neuromorphic systems to be implemented in hardware chips.
PDF Web DOI BibTeX
Empirical Inference Conference Paper A Kernel-based Approach to Direct Action Perception Kroemer, O., Ugur, E., Oztop, E., Peters, J. In International Conference on Robotics and Automation (ICRA 2012), 2605-2610, IEEE, IEEE International Conference on Robotics and Automation (ICRA 2012), May 2012 (Published)
The direct perception of actions allows a robot to predict the afforded actions of observed novel objects. In addition to learning which actions are afforded, the robot must also learn to adapt its actions according to the object being manipulated. In this paper, we present a non-parametric approach to representing the affordance-bearing subparts of objects. This representation forms the basis of a kernel function for computing the similarity between different subparts. Using this kernel function, the robot can learn the required mappings to perform direct action perception. The proposed approach was successfully implemented on a real robot, which could then quickly learn to generalize grasping and pouring actions to novel objects.
PDF Web DOI BibTeX
Empirical Inference Talk A new PET insert for simultaneous PET/MR small animal imaging Wehrl, H., Lankes, K., Hossain, M., Bezrukov, I., Liu, C., Martirosian, P., Reischl, G., Schick, F., Pichler, B. 20th Annual Meeting and Exhibition of the International Society for Magnetic Resonance in Medicine (ISMRM 2012), May 2012 Web BibTeX