Header logo is ei


2012


no image
Generalization of Human Grasping for Multi-Fingered Robot Hands

Ben Amor, H., Kroemer, O., Hillenbrand, U., Neumann, G., Peters, J.

In IEEE/RSJ International Conference on Intelligent Robots and Systems , pages: 2043-2050, IROS, 2012 (inproceedings)

PDF DOI [BibTex]

2012

PDF DOI [BibTex]


no image
Learning Concurrent Motor Skills in Versatile Solution Spaces

Daniel, C., Neumann, G., Peters, J.

In IEEE/RSJ International Conference on Intelligent Robots and Systems , pages: 3591-3597, IROS, 2012 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Learning to Select and Generalize Striking Movements in Robot Table Tennis

Mülling, K., Kober, J., Kroemer, O., Peters, J.

In AAAI Fall Symposium on Robots Learning Interactively from Human Teachers, 2012 (inproceedings)

[BibTex]

[BibTex]


no image
Computational vascular morphometry for the assessment of pulmonary vascular disease based on scale-space particles

Estépar, R., Ross, J., Krissian, K., Schultz, T., Washko, G., Kindlmann, G.

In pages: 1479-1482, IEEE, 9th International Symposium on Biomedical Imaging (ISBI) , 2012 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Hilbert space embedding for Dirichlet Process mixtures

Muandet, K.

In NIPS Workshop on confluence between kernel methods and graphical models, 2012 (inproceedings)

arXiv [BibTex]

arXiv [BibTex]


no image
Causal discovery with scale-mixture model for spatiotemporal variance dependencies

Chen, Z., Zhang, K., Chan, L.

In Advances in Neural Information Processing Systems 25, pages: 1736-1744, (Editors: P Bartlett and FCN Pereira and CJC. Burges and L Bottou and KQ Weinberger), Curran Associates Inc., 26th Annual Conference on Neural Information Processing Systems (NIPS), 2012 (inproceedings)

PDF PDF [BibTex]

PDF PDF [BibTex]


no image
Bridging Offline and Online Social Graph Dynamics

Gomez Rodriguez, M., Rogati, M.

In 21st ACM Conference on Information and Knowledge Management, pages: 2447-2450, (Editors: Chen, X., Lebanon, G., Wang, H. and Zaki, M. J.), ACM, CIKM, 2012 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
A new metric on the manifold of kernel matrices with application to matrix geometric means

Sra, S.

In Advances in Neural Information Processing Systems 25, pages: 144-152, (Editors: P Bartlett and FCN Pereira and CJC. Burges and L Bottou and KQ Weinberger), Curran Associates Inc., 26th Annual Conference on Neural Information Processing Systems (NIPS), 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Conditional mean embeddings as regressors

Grünewälder, S., Lever, G., Baldassarre, L., Patterson, S., Gretton, A., Pontil, M.

In Proceedings of the 29th International Conference on Machine Learning, pages: 1823-1830, (Editors: J Langford and J Pineau), Omnipress, New York, NY, USA, ICML, 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Shortest path distance in random k-nearest neighbor graphs

Alamgir, M., von Luxburg, U.

In Proceedings of the 29th International Conference on Machine Learning, International Machine Learning Society, International Conference on Machine Learning (ICML), 2012 (inproceedings)

PDF Web [BibTex]

PDF Web [BibTex]


no image
Toward Fast Policy Search for Learning Legged Locomotion

Deisenroth, M., Calandra, R., Seyfarth, A., Peters, J.

In IEEE/RSJ International Conference on Intelligent Robots and Systems , pages: 1787-1792, IROS, 2012 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Robot Skill Learning

Peters, J., Kober, J., Mülling, K., Nguyen-Tuong, D., Kroemer, O.

In 20th European Conference on Artificial Intelligence , pages: 40-45, ECAI, 2012 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Towards a learning-theoretic analysis of spike-timing dependent plasticity

Balduzzi, D., Besserve, M.

In Advances in Neural Information Processing Systems 25, pages: 2465-2473, (Editors: P Bartlett and FCN Pereira and CJC. Burges and L Bottou and KQ Weinberger), Curran Associates Inc., 26th Annual Conference on Neural Information Processing Systems (NIPS), 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database

Köhler, R., Hirsch, M., Mohler, B., Schölkopf, B., Harmeling, S.

In Computer Vision - ECCV 2012, LNCS Vol. 7578, pages: 27-40, (Editors: A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, and C. Schmid), Springer, Berlin, Germany, 12th European Conference on Computer Vision, ECCV , 2012 (inproceedings)

Abstract
Motion blur due to camera shake is one of the predominant sources of degradation in handheld photography. Single image blind deconvolution (BD) or motion deblurring aims at restoring a sharp latent image from the blurred recorded picture without knowing the camera motion that took place during the exposure. BD is a long-standing problem, but has attracted much attention recently, cumulating in several algorithms able to restore photos degraded by real camera motion in high quality. In this paper, we present a benchmark dataset for motion deblurring that allows quantitative performance evaluation and comparison of recent approaches featuring non-uniform blur models. To this end, we record and analyse real camera motion, which is played back on a robot platform such that we can record a sequence of sharp images sampling the six dimensional camera motion trajectory. The goal of deblurring is to recover one of these sharp images, and our dataset contains all information to assess how closely various algorithms approximate that goal. In a comprehensive comparison, we evaluate state-of-the-art single image BD algorithms incorporating uniform and non-uniform blur models.

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Towards identifying and validating cognitive correlates in a passive Brain-Computer Interface for detecting Loss of Control

Zander, TO., Pape, AA.

In Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, EMBC, 2012 (inproceedings)

[BibTex]

[BibTex]


no image
Neural correlates of workload and puzzlement during loss of control

Pape, AA., Gerjets, P., Zander, TO.

In Meeting of the EARLI SIG 22 Neuroscience and Education, 2012 (inproceedings)

[BibTex]

[BibTex]


no image
Hypothesis testing using pairwise distances and associated kernels

Sejdinovic, D., Gretton, A., Sriperumbudur, B., Fukumizu, K.

In Proceedings of the 29th International Conference on Machine Learning, pages: 1111-1118, (Editors: J Langford and J Pineau), Omnipress, New York, NY, USA, ICML, 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Efficient Training of Graph-Regularized Multitask SVMs

Widmer, C., Kloft, M., Görnitz, N., Rätsch, G.

In Machine Learning and Knowledge Discovery in Databases - European Conference, ECML/PKDD 2012, LNCS Vol. 7523, pages: 633-647, (Editors: PA Flach and T De Bie and N Cristianini), Springer, Berlin, Germany, ECML, 2012 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Hilbert Space Embeddings of POMDPs

Nishiyama, Y., Boularias, A., Gretton, A., Fukumizu, K.

In Conference on Uncertainty in Artificial Intelligence (UAI), 2012 (inproceedings)

PDF Web [BibTex]

PDF Web [BibTex]


no image
Learning Throwing and Catching Skills

Kober, J., Mülling, K., Peters, J.

In IEEE/RSJ International Conference on Intelligent Robots and Systems , pages: 5167-5168, IROS, 2012 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Maximally Informative Interaction Learning for Scene Exploration

van Hoof, H., Kroemer, O., Ben Amor, H., Peters, J.

In IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 5152-5158, IROS, 2012 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Investigating the Neural Basis of Brain-Computer Interface (BCI)-based Stroke Rehabilitation

Meyer, T., Peters, J., Zander, T., Brötz, D., Soekadar, S., Schölkopf, B., Grosse-Wentrup, M.

In International Conference on NeuroRehabilitation (ICNR) , pages: 617-621, (Editors: JL Pons, D Torricelli, and M Pajaro), Springer, Berlin, Germany, ICNR, 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function

Ortega, P., Grau-Moya, J., Genewein, T., Balduzzi, D., Braun, D.

In Advances in Neural Information Processing Systems 25, pages: 3014-3022, (Editors: P Bartlett and FCN Pereira and CJC. Burges and L Bottou and KQ Weinberger), Curran Associates Inc., 26th Annual Conference on Neural Information Processing Systems (NIPS), 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Algorithms for Learning Markov Field Policies

Boularias, A., Kroemer, O., Peters, J.

In Advances in Neural Information Processing Systems 25, pages: 2186-2194, (Editors: P Bartlett and FCN Pereira and CJC. Burges and L Bottou and KQ Weinberger), Curran Associates Inc., 26th Annual Conference on Neural Information Processing Systems (NIPS), 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Semi-Supervised Domain Adaptation with Copulas

Lopez-Paz, D., Hernandez-Lobato, J., Schölkopf, B.

In Advances in Neural Information Processing Systems 25, pages: 674-682, (Editors: P Bartlett, FCN Pereira, CJC. Burges, L Bottou, and KQ Weinberger), Curran Associates Inc., 26th Annual Conference on Neural Information Processing Systems (NIPS), 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Gradient Weights help Nonparametric Regressors

Kpotufe, S., Boularias, A.

In Advances in Neural Information Processing Systems 25, pages: 2870-2878, (Editors: P Bartlett and FCN Pereira and CJC. Burges and L Bottou and KQ Weinberger), 26th Annual Conference on Neural Information Processing Systems (NIPS), 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
A Blind Deconvolution Approach for Pseudo CT Prediction from MR Image Pairs

Hirsch, M., Hofmann, M., Mantlik, F., Pichler, B., Schölkopf, B., Habeck, M.

In 19th IEEE International Conference on Image Processing (ICIP) , pages: 2953 -2956, IEEE, ICIP, 2012 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
A mixed model approach for joint genetic analysis of alternatively spliced transcript isoforms using RNA-Seq data

Rakitsch, B., Lippert, C., Topa, H., Borgwardt, KM., Honkela, A., Stegle, O.

In 2012 (inproceedings) Submitted

Web [BibTex]

Web [BibTex]


no image
Evaluation of marginal likelihoods via the density of states

Habeck, M.

In Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2012) , 22, pages: 486-494, (Editors: N Lawrence and M Girolami), JMLR: W&CP 22, AISTATS, 2012 (inproceedings)

Abstract
Bayesian model comparison involves the evaluation of the marginal likelihood, the expectation of the likelihood under the prior distribution. Typically, this high-dimensional integral over all model parameters is approximated using Markov chain Monte Carlo methods. Thermodynamic integration is a popular method to estimate the marginal likelihood by using samples from annealed posteriors. Here we show that there exists a robust and flexible alternative. The new method estimates the density of states, which counts the number of states associated with a particular value of the likelihood. If the density of states is known, computation of the marginal likelihood reduces to a one- dimensional integral. We outline a maximum likelihood procedure to estimate the density of states from annealed posterior samples. We apply our method to various likelihoods and show that it is superior to thermodynamic integration in that it is more flexible with regard to the annealing schedule and the family of bridging distributions. Finally, we discuss the relation of our method with Skilling's nested sampling.

PDF [BibTex]

PDF [BibTex]


no image
Distributed multisensory signals acquisition and analysis in dyadic interactions

Tawari, A., Tran, C., Doshi, A., Zander, TO.

In Proceedings of the 2012 ACM Annual Conference on Human Factors in Computing Systems Extended Abstracts, pages: 2261-2266, (Editors: JA Konstan and EH Chi and K Höök), ACM, New York, NY, USA, CHI, 2012 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Measuring Cognitive Load by means of EEG-data - how detailed is the picture we can get?

Scharinger, C., Cierniak, G., Walter, C., Zander, TO., Gerjets, P.

In Meeting of the EARLI SIG 22 Neuroscience and Education, 2012 (inproceedings)

[BibTex]

[BibTex]


no image
Optimal kernel choice for large-scale two-sample tests

Gretton, A., Sriperumbudur, B., Sejdinovic, D., Strathmann, H., Balakrishnan, S., Pontil, M., Fukumizu, K.

In Advances in Neural Information Processing Systems 25, pages: 1214-1222, (Editors: P Bartlett and FCN Pereira and CJC. Burges and L Bottou and KQ Weinberger), Curran Associates Inc., 26th Annual Conference on Neural Information Processing Systems (NIPS), 2012 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
On the Hardness of Domain Adaptation and the Utility of Unlabeled Target Samples

Ben-David, S., Urner, R.

In Algorithmic Learning Theory - 23rd International Conference, 7568, pages: 139-153, Lecture Notes in Computer Science, (Editors: Bshouty, NH. and Stoltz, G and Vayatis, N and Zeugmann, T), Springer Berlin Heidelberg, ALT, 2012 (inproceedings)

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Domain Adaptation–Can Quantity compensate for Quality?

Ben-David, S., Shalev-Shwartz, S., Urner, R.

In International Symposium on Artificial Intelligence and Mathematics, ISAIM, 2012 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Learning from Weak Teachers

Urner, R., Ben-David, S., Shamir, O.

In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics, 22, pages: 1252-1260, (Editors: Lawrence, N. and Girolami, M.), JMLR, AISTATS, 2012 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Adaptive Coding of Actions and Observations

Ortega, PA, Braun, DA

pages: 1-4, NIPS Workshop on Information in Perception and Action, December 2012 (conference)

Abstract
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.

link (url) [BibTex]

link (url) [BibTex]


no image
Free Energy and the Generalized Optimality Equations for Sequential Decision Making

Ortega, PA, Braun, DA

pages: 1-10, 10th European Workshop on Reinforcement Learning (EWRL), July 2012 (conference)

Abstract
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.

link (url) [BibTex]

link (url) [BibTex]

2009


no image
A computational model of human table tennis for robot application

Mülling, K., Peters, J.

In AMS 2009, pages: 57-64, (Editors: Dillmann, R. , J. Beyerer, C. Stiller, M. Zöllner, T. Gindele), Springer, Berlin, Germany, Autonome Mobile Systeme, December 2009 (inproceedings)

Abstract
Table tennis is a difficult motor skill which requires all basic components of a general motor skill learning system. In order to get a step closer to such a generic approach to the automatic acquisition and refinement of table tennis, we study table tennis from a human motor control point of view. We make use of the basic models of discrete human movement phases, virtual hitting points, and the operational timing hypothesis. Using these components, we create a computational model which is aimed at reproducing human-like behavior. We verify the functionality of this model in a physically realistic simulation of a BarrettWAM.

Web DOI [BibTex]

2009

Web DOI [BibTex]


no image
A second order sliding mode controller with polygonal constraints

Dinuzzo, F.

In pages: 6715-6719, IEEE, Piscataway, NJ, USA, 48th IEEE Conference on Decision and Control (CDC), December 2009 (inproceedings)

Abstract
It is presented a discontinuous controller that ensure uniform finite-time zero stabilization of the output for uncertain SISO systems of relative degree two, while keeping the auxiliary system state within a prescribed convex polygon. The proposed method extends applicability of second order sliding modes controllers to the case of uncertain dynamical systems with constraints.

Web DOI [BibTex]

Web DOI [BibTex]


no image
A PAC-Bayesian Approach to Formulation of Clustering Objectives

Seldin, Y., Tishby, N.

In Proceedings of the NIPS 2009 Workshop "Clustering: Science or Art? Towards Principled Approaches", pages: 1-4, NIPS Workshop "Clustering: Science or Art? Towards Principled Approaches", December 2009 (inproceedings)

Abstract
Clustering is a widely used tool for exploratory data analysis. However, the theoretical understanding of clustering is very limited. We still do not have a well-founded answer to the seemingly simple question of “how many clusters are present in the data?”, and furthermore a formal comparison of clusterings based on different optimization objectives is far beyond our abilities. The lack of good theoretical support gives rise to multiple heuristics that confuse the practitioners and stall development of the field. We suggest that the ill-posed nature of clustering problems is caused by the fact that clustering is often taken out of its subsequent application context. We argue that one does not cluster the data just for the sake of clustering it, but rather to facilitate the solution of some higher level task. By evaluation of the clustering’s contribution to the solution of the higher level task it is possible to compare different clusterings, even those obtained by different optimization objectives. In the preceding work it was shown that such an approach can be applied to evaluation and design of co-clustering solutions. Here we suggest that this approach can be extended to other settings, where clustering is applied.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Notes on Graph Cuts with Submodular Edge Weights

Jegelka, S., Bilmes, J.

In pages: 1-6, NIPS Workshop on Discrete Optimization in Machine Learning: Submodularity, Sparsity & Polyhedra (DISCML), December 2009 (inproceedings)

Abstract
Generalizing the cost in the standard min-cut problem to a submodular cost function immediately makes the problem harder. Not only do we prove NP hardness even for nonnegative submodular costs, but also show a lower bound of (|V |1/3) on the approximation factor for the (s, t) cut version of the problem. On the positive side, we propose and compare three approximation algorithms with an overall approximation factor of O(min{|V |,p|E| log |V |}) that appear to do well in practice.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Learning new basic Movements for Robotics

Kober, J., Peters, J.

In AMS 2009, pages: 105-112, (Editors: Dillmann, R. , J. Beyerer, C. Stiller, M. Zöllner, T. Gindele), Springer, Berlin, Germany, Autonome Mobile Systeme, December 2009 (inproceedings)

Abstract
Obtaining novel skills is one of the most important problems in robotics. Machine learning techniques may be a promising approach for automatic and autonomous acquisition of movement policies. However, this requires both an appropriate policy representation and suitable learning algorithms. Employing the most recent form of the dynamical systems motor primitives originally introduced by Ijspeert et al. [1], we show how both discrete and rhythmic tasks can be learned using a concerted approach of both imitation and reinforcement learning, and present our current best performing learning algorithms. Finally, we show that it is possible to include a start-up phase in rhythmic primitives. We apply our approach to two elementary movements, i.e., Ball-in-a-Cup and Ball-Paddling, which can be learned on a real Barrett WAM robot arm at a pace similar to human learning.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
From Motor Learning to Interaction Learning in Robots

Sigaud, O., Peters, J.

In Proceedings of 7ème Journées Nationales de la Recherche en Robotique, pages: 189-195, JNRR, November 2009 (inproceedings)

Abstract
The number of advanced robot systems has been increasing in recent years yielding a large variety of versatile designs with many degrees of freedom. These robots have the potential of being applicable in uncertain tasks outside well-structured industrial settings. However, the complexity of both systems and tasks is often beyond the reach of classical robot programming methods. As a result, a more autonomous solution for robot task acquisition is needed where robots adaptively adjust their behaviour to the encountered situations and required tasks. Learning approaches pose one of the most appealing ways to achieve this goal. However, while learning approaches are of high importance for robotics, we cannot simply use off-the-shelf methods from the machine learning community as these usually do not scale into the domains of robotics due to excessive computational cost as well as a lack of scalability. Instead, domain appropriate approaches are needed. We focus here on several core domains of robot learning. For accurate task execution, we need motor learning capabilities. For fast learning of the motor tasks, imitation learning offers the most promising approach. Self improvement requires reinforcement learning approaches that scale into the domain of complex robots. Finally, for efficient interaction of humans with robot systems, we will need a form of interaction learning. This contribution provides a general introduction to these issues and briefly presents the contributions of the related book chapters to the corresponding research topics.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Detecting Objects in Large Image Collections and Videos by Efficient Subimage Retrieval

Lampert, CH.

In ICCV 2009, pages: 987-994, IEEE Computer Society, Piscataway, NJ, USA, Twelfth IEEE International Conference on Computer Vision, October 2009 (inproceedings)

Abstract
We study the task of detecting the occurrence of objects in large image collections or in videos, a problem that combines aspects of content based image retrieval and object localization. While most previous approaches are either limited to special kinds of queries, or do not scale to large image sets, we propose a new method, efficient subimage retrieval (ESR), which is at the same time very flexible and very efficient. Relying on a two-layered branch-and-bound setup, ESR performs object-based image retrieval in sets of 100,000 or more images within seconds. An extensive evaluation on several datasets shows that ESR is not only very fast, but it also achieves detection accuracies that are on par with or superior to previously published methods for object-based image retrieval.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
A new non-monotonic algorithm for PET image reconstruction

Sra, S., Kim, D., Dhillon, I., Schölkopf, B.

In IEEE - Nuclear Science Symposium Conference Record (NSS/MIC), 2009, pages: 2500-2502, (Editors: B Yu), IEEE, Piscataway, NJ, USA, IEEE Nuclear Science Symposium and Medical Imaging Conference, October 2009 (inproceedings)

Abstract
Maximizing some form of Poisson likelihood (either with or without penalization) is central to image reconstruction algorithms in emission tomography. In this paper we introduce NMML, a non-monotonic algorithm for maximum likelihood PET image reconstruction. NMML offers a simple and flexible procedure that also easily incorporates standard convex regular-ization for doing penalized likelihood estimation. A vast number image reconstruction algorithms have been developed for PET, and new ones continue to be designed. Among these, methods based on the expectation maximization (EM) and ordered-subsets (OS) framework seem to have enjoyed the greatest popularity. Our method NMML differs fundamentally from methods based on EM: i) it does not depend on the concept of optimization transfer (or surrogate functions); and ii) it is a rapidly converging nonmonotonic descent procedure. The greatest strengths of NMML, however, are its simplicity, efficiency, and scalability, which make it especially attractive for tomograph ic reconstruction. We provide a theoretical analysis NMML, and empirically observe it to outperform standard EM based methods, sometimes by orders of magnitude. NMML seamlessly allows integreation of penalties (regularizers) in the likelihood. This ability can prove to be crucial, especially because with the rapidly rising importance of combined PET/MR scanners, one will want to include more “prior” knowledge into the reconstruction.

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Approximation Algorithms for Tensor Clustering

Jegelka, S., Sra, S., Banerjee, A.

In Algorithmic Learning Theory: 20th International Conference, pages: 368-383, (Editors: Gavalda, R. , G. Lugosi, T. Zeugmann, S. Zilles), Springer, Berlin, Germany, ALT, October 2009 (inproceedings)

Abstract
We present the first (to our knowledge) approximation algo- rithm for tensor clustering—a powerful generalization to basic 1D clustering. Tensors are increasingly common in modern applications dealing with complex heterogeneous data and clustering them is a fundamental tool for data analysis and pattern discovery. Akin to their 1D cousins, common tensor clustering formulations are NP-hard to optimize. But, unlike the 1D case no approximation algorithms seem to be known. We address this imbalance and build on recent co-clustering work to derive a tensor clustering algorithm with approximation guarantees, allowing metrics and divergences (e.g., Bregman) as objective functions. Therewith, we answer two open questions by Anagnostopoulos et al. (2008). Our analysis yields a constant approximation factor independent of data size; a worst-case example shows this factor to be tight for Euclidean co-clustering. However, empirically the approximation factor is observed to be conservative, so our method can also be used in practice.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Active learning using mean shift optimization for robot grasping

Kroemer, O., Detry, R., Piater, J., Peters, J.

In Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009), pages: 2610-2615, IEEE Service Center, Piscataway, NJ, USA, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2009 (inproceedings)

Abstract
When children learn to grasp a new object, they often know several possible grasping points from observing a parent‘s demonstration and subsequently learn better grasps by trial and error. From a machine learning point of view, this process is an active learning approach. In this paper, we present a new robot learning framework for reproducing this ability in robot grasping. For doing so, we chose a straightforward approach: first, the robot observes a few good grasps by demonstration and learns a value function for these grasps using Gaussian process regression. Subsequently, it chooses grasps which are optimal with respect to this value function using a mean-shift optimization approach, and tries them out on the real system. Upon every completed trial, the value function is updated, and in the following trials it is more likely to choose even better grasping points. This method exhibits fast learning due to the data-efficiency of Gaussian process regression framework and the fact th at t he mean-shift method provides maxima of this cost function. Experiments were repeatedly carried out successfully on a real robot system. After less than sixty trials, our system has adapted its grasping policy to consistently exhibit successful grasps.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Sparse online model learning for robot control with support vector regression

Nguyen-Tuong, D., Schölkopf, B., Peters, J.

In Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009), pages: 3121-3126, IEEE Service Center, Piscataway, NJ, USA, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2009 (inproceedings)

Abstract
The increasing complexity of modern robots makes it prohibitively hard to accurately model such systems as required by many applications. In such cases, machine learning methods offer a promising alternative for approximating such models using measured data. To date, high computational demands have largely restricted machine learning techniques to mostly offline applications. However, making the robots adaptive to changes in the dynamics and to cope with unexplored areas of the state space requires online learning. In this paper, we propose an approximation of the support vector regression (SVR) by sparsification based on the linear independency of training data. As a result, we obtain a method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques, such as nu-SVR, Gaussian process regression (GPR) and locally weighted projection regression (LWPR).

Web DOI [BibTex]

Web DOI [BibTex]


no image
Causality Discovery with Additive Disturbances: An Information-Theoretical Perspective

Zhang, K., Hyvärinen, A.

In Machine Learning and Knowledge Discovery in Databases, pages: 570-585, (Editors: Buntine, W. , M. Grobelnik, D. Mladenić, J. Shawe-Taylor ), Springer, Berlin, Germany, European Conference on Machine Learning and Knowledge Discovery in Databases: Part II (ECML PKDD '09), September 2009 (inproceedings)

Abstract
We consider causally sufficient acyclic causal models in which the relationship among the variables is nonlinear while disturbances have linear effects, and show that three principles, namely, the causal Markov condition (together with the independence between each disturbance and the corresponding parents), minimum disturbance entropy, and mutual independence of the disturbances, are equivalent. This motivates new and more efficient methods for some causal discovery problems. In particular, we propose to use multichannel blind deconvolution, an extension of independent component analysis, to do Granger causality analysis with instantaneous effects. This approach gives more accurate estimates of the parameters and can easily incorporate sparsity constraints. For additive disturbance-based nonlinear causal discovery, we first make use of the conditional independence relationships to obtain the equivalence class; undetermined causal directions are then found by nonlinear regression and pairwise independence tests. This avoids the brute-force search and greatly reduces the computational load.

PDF PDF DOI [BibTex]

PDF PDF DOI [BibTex]


no image
Implicit Wiener Series Analysis of Epileptic Seizure Recordings

Barbero, A., Franz, M., Drongelen, W., Dorronsoro, J., Schölkopf, B., Grosse-Wentrup, M.

In EMBC 2009, pages: 5304-5307, (Editors: Y Kim and B He and G Worrell and X Pan), IEEE Service Center, Piscataway, NJ, USA, 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, September 2009 (inproceedings)

Abstract
Implicit Wiener series are a powerful tool to build Volterra representations of time series with any degree of nonlinearity. A natural question is then whether higher order representations yield more useful models. In this work we shall study this question for ECoG data channel relationships in epileptic seizure recordings, considering whether quadratic representations yield more accurate classifiers than linear ones. To do so we first show how to derive statistical information on the Volterra coefficient distribution and how to construct seizure classification patterns over that information. As our results illustrate, a quadratic model seems to provide no advantages over a linear one. Nevertheless, we shall also show that the interpretability of the implicit Wiener series provides insights into the inter-channel relationships of the recordings.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]