Header logo is ei


2014


no image
Visualizing Uncertainty in HARDI Tractography Using Superquadric Streamtubes

Wiens, V., Schlaffke, L., Schmidt-Wilcke, T., Schultz, T.

In Eurographics Conference on Visualization, Short Papers, (Editors: Elmqvist, N. and Hlawitschka, M. and Kennedy, J.), EuroVis, 2014 (inproceedings)

Abstract
Standard streamtubes for the visualization of diffusion MRI data are rendered either with a circular or with an elliptic cross section whose aspect ratio indicates the relative magnitudes of the medium and minor eigenvalues. Inspired by superquadric tensor glyphs, we propose to render streamtubes with a superquadric cross section, which develops sharp edges to more clearly convey the orientation of the second and third eigenvectors where they are uniquely defined, while maintaining a circular shape when the smaller two eigenvalues are equal. As a second contribution, we apply our novel superquadric streamtubes to visualize uncertainty in the tracking direction of HARDI tractography, which we represent using a novel propagation uncertainty tensor.

link (url) DOI [BibTex]

2014

link (url) DOI [BibTex]


no image
A Permutation-Based Kernel Conditional Independence Test

Doran, G., Muandet, K., Zhang, K., Schölkopf, B.

In Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence (UAI2014), pages: 132-141, (Editors: Nevin L. Zhang and Jin Tian), AUAI Press Corvallis, Oregon, UAI2014, 2014 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
A unifying view of representer theorems

Argyriou, A., Dinuzzo, F.

In Proceedings of the 31th International Conference on Machine Learning, 32, pages: 748-756, (Editors: Xing, E. P. and Jebera, T.), ICML, 2014 (inproceedings)

PDF PDF [BibTex]

PDF PDF [BibTex]


no image
Riemannian Sparse Coding for Positive Definite Matrices

Cherian, A., Sra, S.

In 13th European Conference on Computer Vision, LNCS 8691, pages: 299-314, (Editors: Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T.), Springer, ECCV, 2014 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Probabilistic ODE Solvers with Runge-Kutta Means

Schober, M., Duvenaud, D., Hennig, P.

In Advances in Neural Information Processing Systems 27, pages: 739-747, (Editors: Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence and K.Q. Weinberger), Curran Associates, Inc., 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (inproceedings)

Web link (url) [BibTex]

Web link (url) [BibTex]


no image
Mask-Specific Inpainting with Deep Neural Networks

Köhler, R., Schuler, C., Schölkopf, B., Harmeling, S.

In Pattern Recognition (GCPR 2014), pages: 523-534, (Editors: X Jiang, J Hornegger, and R Koch), Springer, 2014, Lecture Notes in Computer Science (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Randomized Nonlinear Component Analysis

Lopez-Paz, D., Sra, S., Smola, A., Ghahramani, Z., Schölkopf, B.

In Proceedings of the 31st International Conference on Machine Learning, W&CP 32 (1), pages: 1359-1367, (Editors: Eric P. Xing and Tony Jebara), JMLR, ICML, 2014 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Causal and Anti-Causal Learning in Pattern Recognition for Neuroimaging

Weichwald, S., Schölkopf, B., Ball, T., Grosse-Wentrup, M.

In 4th International Workshop on Pattern Recognition in Neuroimaging (PRNI), IEEE , PRNI, 2014 (inproceedings)

PDF Arxiv DOI [BibTex]

PDF Arxiv DOI [BibTex]


no image
Bayesian Gait Optimization for Bipedal Locomotion

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

In Proceedings of the 8th International Conference on Learning and Intelligent Optimization , LNCS 8426, pages: 274-290, Lecture Notes in Computer Science, (Editors: Pardalos, PM., Resende, MGC., Vogiatzis, C., and Walteros, JL.), Springer, LION, 2014 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Learning Manipulation by Sequencing Motor Primitives with a Two-Armed Robot

Lioutikov, R., Kroemer, O., Peters, J., Maeda, G.

In Proceedings of the 13th International Conference on Intelligent Autonomous Systems, 302, pages: 1601-1611, Advances in Intelligent Systems and Computing, (Editors: Menegatti, E., Michael, N., Berns, K., Yamaguchi, H.), Springer, IAS, 2014 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Kernel Mean Estimation via Spectral Filtering

Muandet, K., Sriperumbudur, B., Schölkopf, B.

In Advances in Neural Information Processing Systems 27, pages: 1-9, (Editors: Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence and K.Q. Weinberger), Curran Associates, Inc., 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (inproceedings)

Web link (url) [BibTex]

Web link (url) [BibTex]


no image
Shaping Social Activity by Incentivizing Users

Farajtabar, M., Du, N., Gomez Rodriguez, M., Valera, I., Zha, H., Song, L.

In Advances in Neural Information Processing Systems 27, (Editors: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, ND., and Weinberger, KQ.), Curran Associates, Inc., 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (inproceedings)

Web link (url) [BibTex]

Web link (url) [BibTex]


no image
Consistency of Causal Inference under the Additive Noise Model

Kpotufe, S., Sgouritsa, E., Janzing, D., Schölkopf, B.

In Proceedings of the 31st International Conference on Machine Learning, W&CP 32 (1), pages: 478-495, (Editors: Eric P. Xing and Tony Jebara), JMLR, ICML, 2014 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Active Learning of Linear Embeddings for Gaussian Processes

Garnett, R., Osborne, M., Hennig, P.

In Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence, pages: 230-239, (Editors: NL Zhang and J Tian), AUAI Press , Corvallis, Oregon, UAI2014, 2014, another link: http://arxiv.org/abs/1310.6740 (inproceedings)

PDF Web [BibTex]

PDF Web [BibTex]


no image
Decoding Index Finger Position from EEG Using Random Forests

Weichwald, S., Meyer, T., Schölkopf, B., Ball, T., Grosse-Wentrup, M.

In 4th International Workshop on Cognitive Information Processing (CIP), IEEE, CIP, 2014 (inproceedings)

PDF Arxiv DOI [BibTex]

PDF Arxiv DOI [BibTex]


no image
An Experimental Comparison of Bayesian Optimization for Bipedal Locomotion

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

In Proceedings of 2014 IEEE International Conference on Robotics and Automation, pages: 1951-1958, IEEE, ICRA, 2014 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Multi-Task Policy Search for Robotics

Deisenroth, M., Englert, P., Peters, J., Fox, D.

In Proceedings of 2014 IEEE International Conference on Robotics and Automation, pages: 3876-3881, IEEE, ICRA, 2014 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Sample-Based Information-Theoretic Stochastic Optimal Control

Lioutikov, R., Paraschos, A., Peters, J., Neumann, G.

In Proceedings of 2014 IEEE International Conference on Robotics and Automation, pages: 3896-3902, IEEE, ICRA, 2014 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Probabilistic Shortest Path Tractography in DTI Using Gaussian Process ODE Solvers

Schober, M., Kasenburg, N., Feragen, A., Hennig, P., Hauberg, S.

In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014, Lecture Notes in Computer Science Vol. 8675, pages: 265-272, (Editors: P. Golland, N. Hata, C. Barillot, J. Hornegger and R. Howe), Springer, Heidelberg, MICCAI, 2014 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Estimating Causal Effects by Bounding Confounding

Geiger, P., Janzing, D., Schölkopf, B.

In Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence , pages: 240-249 , (Editors: Nevin L. Zhang and Jin Tian), AUAI Press Corvallis, Oregon , UAI, 2014 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Kernel Mean Estimation and Stein Effect

Muandet, K., Fukumizu, K., Sriperumbudur, B., Gretton, A., Schölkopf, B.

In Proceedings of the 31st International Conference on Machine Learning, W&CP 32 (1), pages: 10-18, (Editors: Eric P. Xing and Tony Jebara), JMLR, ICML, 2014 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Active Reward Learning

Daniel, C., Viering, M., Metz, J., Kroemer, O., Peters, J.

In Proceedings of Robotics: Science & Systems, (Editors: Fox, D., Kavraki, LE., and Kurniawati, H.), RSS, 2014 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Multi-modal filtering for non-linear estimation

Kamthe, S., Peters, J., Deisenroth, M.

In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pages: 7979-7983, IEEE, ICASSP, 2014 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Inferring latent structures via information inequalities

Chaves, R., Luft, L., Maciel, T., Gross, D., Janzing, D., Schölkopf, B.

In Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence, pages: 112-121, (Editors: NL Zhang and J Tian), AUAI Press, Corvallis, Oregon, UAI, 2014 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Re-ranking Approach to Classification in Large-scale Power-law Distributed Category Systems

Babbar, R., Partalas, I., Gaussier, E., Amini, M.

In Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval, pages: 1059-1062, (Editors: S Geva and A Trotman and P Bruza and CLA Clarke and K Järvelin), ACM, New York, NY, USA, SIGIR, 2014 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Policy Search For Learning Robot Control Using Sparse Data

Bischoff, B., Nguyen-Tuong, D., van Hoof, H., McHutchon, A., Rasmussen, C., Knoll, A., Peters, J., Deisenroth, M.

In Proceedings of 2014 IEEE International Conference on Robotics and Automation, pages: 3882-3887, IEEE, ICRA, 2014 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Learning to Unscrew a Light Bulb from Demonstrations

Manschitz, S., Kober, J., Gienger, M., Peters, J.

In Proceedings for the joint conference of ISR 2014, 45th International Symposium on Robotics and Robotik 2014, 2014 (inproceedings)

[BibTex]

[BibTex]


no image
Towards Neurofeedback Training of Associative Brain Areas for Stroke Rehabilitation

Özdenizci, O., Meyer, T., Cetin, M., Grosse-Wentrup, M.

In Proceedings of the 6th International Brain-Computer Interface Conference, (Editors: G Müller-Putz and G Bauernfeind and C Brunner and D Steyrl and S Wriessnegger and R Scherer), 2014 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature

Gunter, T., Osborne, M., Garnett, R., Hennig, P., Roberts, S.

In Advances in Neural Information Processing Systems 27, pages: 2789-2797, (Editors: Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence and K.Q. Weinberger), Curran Associates, Inc., 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (inproceedings)

Web link (url) [BibTex]

Web link (url) [BibTex]


no image
Scalable Kernel Methods via Doubly Stochastic Gradients

Dai, B., Xie, B., He, N., Liang, Y., Raj, A., Balcan, M., Song, L.

Advances in Neural Information Processing Systems 27, pages: 3041-3049, (Editors: Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence and K.Q. Weinberger), 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (conference)

link (url) [BibTex]

link (url) [BibTex]


no image
Learning Economic Parameters from Revealed Preferences

Balcan, M., Daniely, A., Mehta, R., Urner, R., Vazirani, V. V.

In Web and Internet Economics - 10th International Conference, 8877, pages: 338-353, Lecture Notes in Computer Science, (Editors: Liu, T.-Y. and Qi, Q. and Ye, Y.), WINE, 2014 (inproceedings)

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Fast Newton methods for the group fused lasso

Wytock, M., Sra, S., Kolter, J. Z.

In Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence, pages: 888-897, (Editors: Zhang, N. L. and Tian, J.), AUAI Press, UAI, 2014 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Mind the Gap: Subspace based Hierarchical Domain Adaptation

Raj, A., Namboodiri, V., Tuytelaars, T.

Transfer and Multi-task learning Workshop in Advances in Neural Information System Conference 27, 2014 (conference)

link (url) [BibTex]

link (url) [BibTex]


no image
Localized Complexities for Transductive Learning

Tolstikhin, I., Blanchard, G., Kloft, M.

In Proceedings of the 27th Conference on Learning Theory, 35, pages: 857-884, (Editors: Balcan, M.-F. and Feldman, V. and Szepesvári, C.), JMLR, COLT, 2014 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Efficient Structured Matrix Rank Minimization

Yu, A. W., Ma, W., Yu, Y., Carbonell, J., Sra, S.

Advances in Neural Information Processing Systems 27, pages: 1350-1358, (Editors: Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence and K.Q. Weinberger), Curran Associates, Inc., 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (conference)

link (url) [BibTex]

link (url) [BibTex]


no image
Towards building a Crowd-Sourced Sky Map

Lang, D., Hogg, D., Schölkopf, B.

In Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, JMLR W\&CP 33, pages: 549–557, (Editors: S. Kaski and J. Corander), JMLR.org, AISTATS, 2014 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Incremental Local Gaussian Regression

Meier, F., Hennig, P., Schaal, S.

In Advances in Neural Information Processing Systems 27, pages: 972-980, (Editors: Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence and K.Q. Weinberger), 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014, clmc (inproceedings)

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Learning to Deblur

Schuler, C. J., Hirsch, M., Harmeling, S., Schölkopf, B.

In NIPS 2014 Deep Learning and Representation Learning Workshop, 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Efficient Bayesian Local Model Learning for Control

Meier, F., Hennig, P., Schaal, S.

In Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pages: 2244 - 2249, IROS, 2014, clmc (inproceedings)

Abstract
Model-based control is essential for compliant controland force control in many modern complex robots, like humanoidor disaster robots. Due to many unknown and hard tomodel nonlinearities, analytical models of such robots are oftenonly very rough approximations. However, modern optimizationcontrollers frequently depend on reasonably accurate models,and degrade greatly in robustness and performance if modelerrors are too large. For a long time, machine learning hasbeen expected to provide automatic empirical model synthesis,yet so far, research has only generated feasibility studies butno learning algorithms that run reliably on complex robots.In this paper, we combine two promising worlds of regressiontechniques to generate a more powerful regression learningsystem. On the one hand, locally weighted regression techniquesare computationally efficient, but hard to tune due to avariety of data dependent meta-parameters. On the other hand,Bayesian regression has rather automatic and robust methods toset learning parameters, but becomes quickly computationallyinfeasible for big and high-dimensional data sets. By reducingthe complexity of Bayesian regression in the spirit of local modellearning through variational approximations, we arrive at anovel algorithm that is computationally efficient and easy toinitialize for robust learning. Evaluations on several datasetsdemonstrate very good learning performance and the potentialfor a general regression learning tool for robotics.

PDF link (url) DOI [BibTex]

PDF link (url) DOI [BibTex]


no image
The sample complexity of agnostic learning under deterministic labels

Ben-David, S., Urner, R.

In Proceedings of the 27th Conference on Learning Theory, 35, pages: 527-542, (Editors: Balcan, M.-F. and Feldman, V. and Szepesvári, C.), JMLR, COLT, 2014 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Towards an optimal stochastic alternating direction method of multipliers

Azadi, S., Sra, S.

Proceedings of the 31st International Conference on Machine Learning, 32, pages: 620-628, (Editors: Xing, E. P. and Jebara, T.), JMLR, ICML, 2014 (conference)

link (url) [BibTex]

link (url) [BibTex]


no image
Open Problem: Finding Good Cascade Sampling Processes for the Network Inference Problem

Gomez Rodriguez, M., Song, L., Schölkopf, B.

Proceedings of the 27th Conference on Learning Theory, 35, pages: 1276-1279, (Editors: Balcan, M.-F. and Szepesvári, C.), JMLR.org, COLT, 2014 (conference)

PDF [BibTex]

PDF [BibTex]


no image
Curiosity-driven learning with Context Tree Weighting

Peng, Z, Braun, DA

pages: 366-367, IEEE, Piscataway, NJ, USA, 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-EPIROB), October 2014 (conference)

Abstract
In the first simulation, the intrinsic motivation of the agent was given by measuring learning progress through reduction in informational surprise (Figure 1 A-C). This way the agent should first learn the action that is easiest to learn (a1), and then switch to other actions that still allow for learning (a2) and ignore actions that cannot be learned at all (a3). This is exactly what we found in our simple environment. Compared to the original developmental learning algorithm based on learning progress proposed by Oudeyer [2], our Context Tree Weighting approach does not require local experts to do prediction, rather it learns the conditional probability distribution over observations given action in one structure. In the second simulation, the intrinsic motivation of the agent was given by measuring compression progress through improvement in compressibility (Figure 1 D-F). The agent behaves similarly: the agent first concentrates on the action with the most predictable consequence and then switches over to the regular action where the consequence is more difficult to predict, but still learnable. Unlike the previous simulation, random actions are also interesting to some extent because the compressed symbol strings use 8-bit representations, while only 2 bits are required for our observation space. Our preliminary results suggest that Context Tree Weighting might provide a useful representation to study problems of development.

DOI [BibTex]

DOI [BibTex]


no image
Monte Carlo methods for exact & efficient solution of the generalized optimality equations

Ortega, PA, Braun, DA, Tishby, N

pages: 4322-4327, IEEE, Piscataway, NJ, USA, IEEE International Conference on Robotics and Automation (ICRA), June 2014 (conference)

Abstract
Previous work has shown that classical sequential decision making rules, including expectimax and minimax, are limit cases of a more general class of bounded rational planning problems that trade off the value and the complexity of the solution, as measured by its information divergence from a given reference. This allows modeling a range of novel planning problems having varying degrees of control due to resource constraints, risk-sensitivity, trust and model uncertainty. However, so far it has been unclear in what sense information constraints relate to the complexity of planning. In this paper, we introduce Monte Carlo methods to solve the generalized optimality equations in an efficient \& exact way when the inverse temperatures in a generalized decision tree are of the same sign. These methods highlight a fundamental relation between inverse temperatures and the number of Monte Carlo proposals. In particular, it is seen that the number of proposals is essentially independent of the size of the decision tree.

link (url) DOI [BibTex]

link (url) DOI [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
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
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
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]