Header logo is


2019


no image
Neural Signatures of Motor Skill in the Resting Brain

Ozdenizci, O., Meyer, T., Wichmann, F., Peters, J., Schölkopf, B., Cetin, M., Grosse-Wentrup, M.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (SMC 2019), October 2019 (conference) Accepted

ei

[BibTex]

2019


[BibTex]


Thumb xl distributed pt control
Predictive Triggering for Distributed Control of Resource Constrained Multi-agent Systems

Mastrangelo, J. M., Baumann, D., Trimpe, S.

In Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems, 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems (NecSys), September 2019 (inproceedings) Accepted

ics

arXiv PDF [BibTex]

arXiv PDF [BibTex]


no image
Beta Power May Mediate the Effect of Gamma-TACS on Motor Performance

Mastakouri, A., Schölkopf, B., Grosse-Wentrup, M.

Engineering in Medicine and Biology Conference (EMBC), July 2019 (conference) Accepted

ei

arXiv PDF [BibTex]

arXiv PDF [BibTex]


Thumb xl acc pulse ctrl
Event-triggered Pulse Control with Model Learning (if Necessary)

Baumann, D., Solowjow, F., Johansson, K. H., Trimpe, S.

In Proceedings of the American Control Conference, pages: 792-797, American Control Conference (ACC), July 2019 (inproceedings)

ics

arXiv PDF [BibTex]

arXiv PDF [BibTex]


no image
The Incomplete Rosetta Stone problem: Identifiability results for Multi-view Nonlinear ICA

Gresele*, L., Rubenstein*, P. K., Mehrjou, A., Locatello, F., Schölkopf, B.

Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence (UAI), pages: 53, (Editors: Amir Globerson and Ricardo Silva), AUAI Press, July 2019, *equal contribution (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


Thumb xl pic
Data-driven inference of passivity properties via Gaussian process optimization

Romer, A., Trimpe, S., Allgöwer, F.

In Proceedings of the European Control Conference, European Control Conference (ECC), June 2019 (inproceedings) Accepted

ics

PDF [BibTex]

PDF [BibTex]


no image
Kernel Mean Matching for Content Addressability of GANs

Jitkrittum*, W., Sangkloy*, P., Gondal, M. W., Raj, A., Hays, J., Schölkopf, B.

Proceedings of the 36th International Conference on Machine Learning (ICML), 97, pages: 3140-3151, Proceedings of Machine Learning Research, (Editors: Chaudhuri, Kamalika and Salakhutdinov, Ruslan), PMLR, June 2019, *equal contribution (conference)

ei

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

Locatello, F., Bauer, S., Lucic, M., Raetsch, G., Gelly, S., Schölkopf, B., Bachem, O.

Proceedings of the 36th International Conference on Machine Learning (ICML), 97, pages: 4114-4124, Proceedings of Machine Learning Research, (Editors: Chaudhuri, Kamalika and Salakhutdinov, Ruslan), PMLR, June 2019 (conference)

ei

PDF link (url) [BibTex]

PDF link (url) [BibTex]


Thumb xl cvpr2019 demo v2.001
Local Temporal Bilinear Pooling for Fine-grained Action Parsing

Zhang, Y., Tang, S., Muandet, K., Jarvers, C., Neumann, H.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Fine-grained temporal action parsing is important in many applications, such as daily activity understanding, human motion analysis, surgical robotics and others requiring subtle and precise operations in a long-term period. In this paper we propose a novel bilinear pooling operation, which is used in intermediate layers of a temporal convolutional encoder-decoder net. In contrast to other work, our proposed bilinear pooling is learnable and hence can capture more complex local statistics than the conventional counterpart. In addition, we introduce exact lower-dimension representations of our bilinear forms, so that the dimensionality is reduced with neither information loss nor extra computation. We perform intensive experiments to quantitatively analyze our model and show the superior performances to other state-of-the-art work on various datasets.

ei ps

Code video demo pdf link (url) [BibTex]

Code video demo pdf link (url) [BibTex]


no image
Generate Semantically Similar Images with Kernel Mean Matching

Jitkrittum*, W., Sangkloy*, P., Gondal, M. W., Raj, A., Hays, J., Schölkopf, B.

6th Workshop Women in Computer Vision (WiCV) (oral presentation), June 2019, *equal contribution (conference) Accepted

ei

[BibTex]

[BibTex]


Thumb xl coverimage1
Trajectory-Based Off-Policy Deep Reinforcement Learning

Doerr, A., Volpp, M., Toussaint, M., Trimpe, S., Daniel, C.

In Proceedings of the International Conference on Machine Learning (ICML), International Conference on Machine Learning (ICML), June 2019 (inproceedings) Accepted

Abstract
Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently get stuck in local optima. This work addresses these weaknesses by combining recent improvements in the reuse of off-policy data and exploration in parameter space with deterministic behavioral policies. The resulting objective is amenable to standard neural network optimization strategies like stochastic gradient descent or stochastic gradient Hamiltonian Monte Carlo. Incorporation of previous rollouts via importance sampling greatly improves data-efficiency, whilst stochastic optimization schemes facilitate the escape from local optima. We evaluate the proposed approach on a series of continuous control benchmark tasks. The results show that the proposed algorithm is able to successfully and reliably learn solutions using fewer system interactions than standard policy gradient methods.

ics

arXiv PDF [BibTex]

arXiv PDF [BibTex]


no image
Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness

Suter, R., Miladinovic, D., Schölkopf, B., Bauer, S.

Proceedings of the 36th International Conference on Machine Learning (ICML), 97, pages: 6056-6065, Proceedings of Machine Learning Research, (Editors: Chaudhuri, Kamalika and Salakhutdinov, Ruslan), PMLR, June 2019 (conference)

ei

PDF link (url) [BibTex]

PDF link (url) [BibTex]


Thumb xl trimpe2019resource image
Resource-aware IoT Control: Saving Communication through Predictive Triggering

Trimpe, S., Baumann, D.

IEEE Internet of Things Journal, 6(3):5013-5028, June 2019 (article)

Abstract
The Internet of Things (IoT) interconnects multiple physical devices in large-scale networks. When the 'things' coordinate decisions and act collectively on shared information, feedback is introduced between them. Multiple feedback loops are thus closed over a shared, general-purpose network. Traditional feedback control is unsuitable for design of IoT control because it relies on high-rate periodic communication and is ignorant of the shared network resource. Therefore, recent event-based estimation methods are applied herein for resource-aware IoT control allowing agents to decide online whether communication with other agents is needed, or not. While this can reduce network traffic significantly, a severe limitation of typical event-based approaches is the need for instantaneous triggering decisions that leave no time to reallocate freed resources (e.g., communication slots), which hence remain unused. To address this problem, novel predictive and self triggering protocols are proposed herein. From a unified Bayesian decision framework, two schemes are developed: self triggers that predict, at the current triggering instant, the next one; and predictive triggers that check at every time step, whether communication will be needed at a given prediction horizon. The suitability of these triggers for feedback control is demonstrated in hardware experiments on a cart-pole, and scalability is discussed with a multi-vehicle simulation.

ics

PDF arXiv DOI [BibTex]

PDF arXiv DOI [BibTex]


no image
First-Order Adversarial Vulnerability of Neural Networks and Input Dimension

Simon-Gabriel, C., Ollivier, Y., Bottou, L., Schölkopf, B., Lopez-Paz, D.

Proceedings of the 36th International Conference on Machine Learning (ICML), 97, pages: 5809-5817, Proceedings of Machine Learning Research, (Editors: Chaudhuri, Kamalika and Salakhutdinov, Ruslan), PMLR, June 2019 (conference)

ei

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models

Ialongo, A. D., Van Der Wilk, M., Hensman, J., Rasmussen, C. E.

In Proceedings of the 36th International Conference on Machine Learning (ICML), 97, pages: 2931-2940, Proceedings of Machine Learning Research, (Editors: Chaudhuri, Kamalika and Salakhutdinov, Ruslan), PMLR, June 2019 (inproceedings)

ei

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Meta learning variational inference for prediction

Gordon, J., Bronskill, J., Bauer, M., Nowozin, S., Turner, R.

7th International Conference on Learning Representations (ICLR), May 2019 (conference) Accepted

ei

arXiv link (url) [BibTex]

arXiv link (url) [BibTex]


no image
Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning

Lutter, M., Ritter, C., Peters, J.

7th International Conference on Learning Representations (ICLR), May 2019 (conference) Accepted

ei

link (url) [BibTex]

link (url) [BibTex]


no image
DeepOBS: A Deep Learning Optimizer Benchmark Suite

Schneider, F., Balles, L., Hennig, P.

7th International Conference on Learning Representations (ICLR), May 2019 (conference) Accepted

ei pn

link (url) [BibTex]

link (url) [BibTex]


no image
Disentangled State Space Models: Unsupervised Learning of Dynamics across Heterogeneous Environments

Miladinović*, D., Gondal*, M. W., Schölkopf, B., Buhmann, J. M., Bauer, S.

Deep Generative Models for Highly Structured Data Workshop at ICLR, May 2019, *equal contribution (conference) Accepted

ei

link (url) [BibTex]

link (url) [BibTex]


no image
SOM-VAE: Interpretable Discrete Representation Learning on Time Series

Fortuin, V., Hüser, M., Locatello, F., Strathmann, H., Rätsch, G.

7th International Conference on Learning Representations (ICLR), May 2019 (conference) Accepted

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Resampled Priors for Variational Autoencoders

Bauer, M., Mnih, A.

22nd International Conference on Artificial Intelligence and Statistics, April 2019 (conference) Accepted

ei

arXiv [BibTex]

arXiv [BibTex]


no image
Semi-Generative Modelling: Covariate-Shift Adaptation with Cause and Effect Features

von Kügelgen, J., Mey, A., Loog, M.

22nd International Conference on Artificial Intelligence and Statistics (AISTATS), April 2019 (conference) Accepted

ei

[BibTex]

[BibTex]


Thumb xl testbed v5
Feedback Control Goes Wireless: Guaranteed Stability over Low-power Multi-hop Networks

(Best Paper Award)

Mager, F., Baumann, D., Jacob, R., Thiele, L., Trimpe, S., Zimmerling, M.

In Proceedings of the 10th ACM/IEEE International Conference on Cyber-Physical Systems, pages: 97-108, 10th ACM/IEEE International Conference on Cyber-Physical Systems, April 2019 (inproceedings)

Abstract
Closing feedback loops fast and over long distances is key to emerging applications; for example, robot motion control and swarm coordination require update intervals below 100 ms. Low-power wireless is preferred for its flexibility, low cost, and small form factor, especially if the devices support multi-hop communication. Thus far, however, closed-loop control over multi-hop low-power wireless has only been demonstrated for update intervals on the order of multiple seconds. This paper presents a wireless embedded system that tames imperfections impairing control performance such as jitter or packet loss, and a control design that exploits the essential properties of this system to provably guarantee closed-loop stability for linear dynamic systems. Using experiments on a testbed with multiple cart-pole systems, we are the first to demonstrate the feasibility and to assess the performance of closed-loop control and coordination over multi-hop low-power wireless for update intervals from 20 ms to 50 ms.

ics

arXiv PDF DOI Project Page [BibTex]

arXiv PDF DOI Project Page [BibTex]


no image
Sobolev Descent

Mroueh, Y., Sercu, T., Raj, A.

22nd International Conference on Artificial Intelligence and Statistics (AISTATS), April 2019 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Fast and Robust Shortest Paths on Manifolds Learned from Data

Arvanitidis, G., Hauberg, S., Hennig, P., Schober, M.

22nd International Conference on Artificial Intelligence and Statistics (AISTATS), April 2019 (conference) Accepted

ei pn

[BibTex]

[BibTex]


no image
Data scarcity, robustness and extreme multi-label classification

Babbar, R., Schölkopf, B.

Machine Learning, Special Issue of the ECML PKDD 2019 Journal Track, March 2019 (article)

ei

DOI [BibTex]

DOI [BibTex]


Thumb xl journal iav
Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study

Neumann-Brosig, M., Marco, A., Schwarzmann, D., Trimpe, S.

IEEE Transactions on Control Systems Technology, 2019 (article) Accepted

Abstract
Bayesian optimization is proposed for automatic learning of optimal controller parameters from experimental data. A probabilistic description (a Gaussian process) is used to model the unknown function from controller parameters to a user-defined cost. The probabilistic model is updated with data, which is obtained by testing a set of parameters on the physical system and evaluating the cost. In order to learn fast, the Bayesian optimization algorithm selects the next parameters to evaluate in a systematic way, for example, by maximizing information gain about the optimum. The algorithm thus iteratively finds the globally optimal parameters with only few experiments. Taking throttle valve control as a representative industrial control example, the proposed auto-tuning method is shown to outperform manual calibration: it consistently achieves better performance with a low number of experiments. The proposed auto-tuning framework is flexible and can handle different control structures and objectives.

ics

arXiv (PDF) DOI Project Page [BibTex]

arXiv (PDF) DOI Project Page [BibTex]


no image
Enhancing Human Learning via Spaced Repetition Optimization

Tabibian, B., Upadhyay, U., De, A., Zarezade, A., Schölkopf, B., Gomez Rodriguez, M.

Proceedings of the National Academy of Sciences, 2019, PNAS published ahead of print January 22, 2019 (article)

ei

DOI Project Page Project Page [BibTex]

DOI Project Page Project Page [BibTex]


Thumb xl screenshot 2019 03 25 at 14.29.22
Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots

Büchler, D., Calandra, R., Peters, J.

2019 (article) Submitted

Abstract
High-speed and high-acceleration movements are inherently hard to control. Applying learning to the control of such motions on anthropomorphic robot arms can improve the accuracy of the control but might damage the system. The inherent exploration of learning approaches can lead to instabilities and the robot reaching joint limits at high speeds. Having hardware that enables safe exploration of high-speed and high-acceleration movements is therefore desirable. To address this issue, we propose to use robots actuated by Pneumatic Artificial Muscles (PAMs). In this paper, we present a four degrees of freedom (DoFs) robot arm that reaches high joint angle accelerations of up to 28000 °/s^2 while avoiding dangerous joint limits thanks to the antagonistic actuation and limits on the air pressure ranges. With this robot arm, we are able to tune control parameters using Bayesian optimization directly on the hardware without additional safety considerations. The achieved tracking performance on a fast trajectory exceeds previous results on comparable PAM-driven robots. We also show that our system can be controlled well on slow trajectories with PID controllers due to careful construction considerations such as minimal bending of cables, lightweight kinematics and minimal contact between PAMs and PAMs with the links. Finally, we propose a novel technique to control the the co-contraction of antagonistic muscle pairs. Experimental results illustrate that choosing the optimal co-contraction level is vital to reach better tracking performance. Through the use of PAM-driven robots and learning, we do a small step towards the future development of robots capable of more human-like motions.

ei

Arxiv Video [BibTex]


no image
AReS and MaRS Adversarial and MMD-Minimizing Regression for SDEs

Abbati*, G., Wenk*, P., Osborne, M. A., Krause, A., Schölkopf, B., Bauer, S.

Proceedings of the 36th International Conference on Machine Learning (ICML), 97, pages: 1-10, Proceedings of Machine Learning Research, (Editors: Chaudhuri, Kamalika and Salakhutdinov, Ruslan), PMLR, 2019, *equal contribution (conference)

ei

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Inferring causation from time series with perspectives in Earth system sciences

Runge, J., Bathiany, S., Bollt, E., Camps-Valls, G., Coumou, D., Deyle, E., Glymour, C., Kretschmer, M., Mahecha, M., van Nes, E., Peters, J., Quax, R., Reichstein, M., Scheffer, M. S. B., Spirtes, P., Sugihara, G., Sun, J., Zhang, K., Zscheischler, J.

Nature Communications, 2019 (article) In revision

ei

[BibTex]

[BibTex]


no image
Kernel Stein Tests for Multiple Model Comparison

Lim, J. N., Yamada, M., Schölkopf, B., Jitkrittum, W.

2019 (conference) Submitted

ei

[BibTex]

[BibTex]


no image
MYND: A Platform for Large-scale Neuroscientific Studies

Hohmann, M. R., Hackl, M., Wirth, B., Zaman, T., Enficiaud, R., Grosse-Wentrup, M., Schölkopf, B.

Proceedings of the 2019 Conference on Human Factors in Computing Systems (CHI), 2019 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
A Kernel Stein Test for Comparing Latent Variable Models

Kanagawa, H., Jitkrittum, W., Mackey, L., Fukumizu, K., Gretton, A.

2019 (conference) Submitted

ei

arXiv [BibTex]

arXiv [BibTex]


no image
Fisher Efficient Inference of Intractable Models

Liu, S., Kanamori, T., Jitkrittum, W., Chen, Y.

2019 (conference) Submitted

ei

arXiv [BibTex]

arXiv [BibTex]


no image
Fast Gaussian Process Based Gradient Matching for Parameter Identification in Systems of Nonlinear ODEs

Wenk, P., Gotovos, A., Bauer, S., Gorbach, N., Krause, A., Buhmann, J. M.

22nd International Conference on Artificial Intelligence and Statistics (AISTATS), 2019 (conference) Accepted

ei

PDF [BibTex]

PDF [BibTex]


Thumb xl rae
From Variational to Deterministic Autoencoders

Ghosh*, P., Sajjadi*, M. S. M., Vergari, A., Black, M. J., Schölkopf, B.

2019, *equal contribution (conference) Submitted

Abstract
Variational Autoencoders (VAEs) provide a theoretically-backed framework for deep generative models. However, they often produce “blurry” images, which is linked to their training objective. Sampling in the most popular implementation, the Gaussian VAE, can be interpreted as simply injecting noise to the input of a deterministic decoder. In practice, this simply enforces a smooth latent space structure. We challenge the adoption of the full VAE framework on this specific point in favor of a simpler, deterministic one. Specifically, we investigate how substituting stochasticity with other explicit and implicit regularization schemes can lead to a meaningful latent space without having to force it to conform to an arbitrarily chosen prior. To retrieve a generative mechanism for sampling new data points, we propose to employ an efficient ex-post density estimation step that can be readily adopted both for the proposed deterministic autoencoders as well as to improve sample quality of existing VAEs. We show in a rigorous empirical study that regularized deterministic autoencoding achieves state-of-the-art sample quality on the common MNIST, CIFAR-10 and CelebA datasets.

ei ps

arXiv [BibTex]

2009


no image
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization

Lampert, C., Blaschko, M., Hofmann, T.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(12):2129-2142, December 2009 (article)

Abstract
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To estimate the object‘s location, one can take a sliding window approach, but this strongly increases the computational cost because the classifier or similarity function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages. It converges to a globally optimal solution typically in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive or sliding window search. We show how our method is applicable to different object detection and image retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest-neighbor classifiers based on the chi^2 distance. We demonstrate state-of-the-art localization performance of the resulting systems on the UIUC Cars data set, the PASCAL VOC 2006 data set, and in the PASCAL VOC 2007 competition.

ei

PDF Web DOI [BibTex]

2009


PDF Web DOI [BibTex]


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.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Generation of three-dimensional random rotations in fitting and matching problems

Habeck, M.

Computational Statistics, 24(4):719-731, December 2009 (article)

Abstract
An algorithm is developed to generate random rotations in three-dimensional space that follow a probability distribution arising in fitting and matching problems. The rotation matrices are orthogonally transformed into an optimal basis and then parameterized using Euler angles. The conditional distributions of the three Euler angles have a very simple form: the two azimuthal angles can be decoupled by sampling their sum and difference from a von Mises distribution; the cosine of the polar angle is exponentially distributed and thus straighforward to generate. Simulation results are shown and demonstrate the effectiveness of the method. The algorithm is compared to other methods for generating random rotations such as a random walk Metropolis scheme and a Gibbs sampling algorithm recently introduced by Green and Mardia. Finally, the algorithm is applied to a probabilistic version of the Procrustes problem of fitting two point sets and applied in the context of protein structure superposition.

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning

Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J.

Neural Networks, 22(10):1399-1410, December 2009 (article)

Abstract
Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a policy that is different from the currently optimized policy. A common approach is to use importance sampling techniques for compensating for the bias of value function estimators caused by the difference between the data-sampling policy and the target policy. However, existing off-policy methods often do not take the variance of the value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a variant of cross-validation. We demonstrate the usefulness of the proposed approach through simulations.

ei

PDF Web DOI [BibTex]

PDF 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.

ei

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.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Guest editorial: special issue on structured prediction

Parker, C., Altun, Y., Tadepalli, P.

Machine Learning, 77(2-3):161-164, December 2009 (article)

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Structured prediction by joint kernel support estimation

Lampert, CH., Blaschko, MB.

Machine Learning, 77(2-3):249-269, December 2009 (article)

ei

PDF DOI [BibTex]

PDF DOI [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.

ei

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.

ei

PDF Web [BibTex]

PDF Web [BibTex]