Publications | Empirical Inference - Max Planck Institute for Intelligent Systems

Twenty-Second Annual Computational Neuroscience Meeting (CNS*2013), July 2013, journal = {BMC Neuroscience}, year = {2013}, month = {7}, volume = {14}, number = {Supplement 1}, pages = {A1}, (talk)

Web [BibTex]

2013

Logothetis, N., Eschenko, O., Murayama, Y., Augath, M., Steudel, T., Evrard, H., Besserve, M., Oeltermann, A. Studying large-scale brain networks: electrical stimulation and neural-event-triggered fMRI Twenty-Second Annual Computational Neuroscience Meeting (CNS*2013), July 2013, journal = {BMC Neuroscience}, year = {2013}, month = {7}, volume = {14}, number = {Supplement 1}, pages = {A1}, (talk)

Web [BibTex]

MR-Based Attenuation Correction for Combined Brain PET/MR: Robustness of Atlas- and Pattern Recognition Method to Atlas Registration Failures

Mantlik, F., Bezrukov, I., Hofmann, M., Schölkopf, B., Pichler, B.

IEEE Nuclear Science Symposium and Medical Imaging Conference (IEEE MIC), 2013 (talk)

[BibTex]

Mantlik, F., Bezrukov, I., Hofmann, M., Schölkopf, B., Pichler, B. MR-Based Attenuation Correction for Combined Brain PET/MR: Robustness of Atlas- and Pattern Recognition Method to Atlas Registration Failures IEEE Nuclear Science Symposium and Medical Imaging Conference (IEEE MIC), 2013 (talk)

[BibTex]

Domain Generalization via Invariant Feature Representation

Muandet, K.

30th International Conference on Machine Learning (ICML2013), 2013 (talk)

PDF [BibTex]

Muandet, K. Domain Generalization via Invariant Feature Representation 30th International Conference on Machine Learning (ICML2013), 2013 (talk)

PDF [BibTex]

Random Projections (Computational and Biological Learning Lab, University of Cambridge, 2013)

Lopez-Paz, D., Duvenaud, D.

2013 (talk)

PDF Web [BibTex]

Lopez-Paz, D., Duvenaud, D. Random Projections (Computational and Biological Learning Lab, University of Cambridge, 2013) 2013 (talk)

PDF Web [BibTex]

2009

Machine Learning for Brain-Computer Interfaces

Hill, NJ.

Mini-Symposia on Assistive Machine Learning for People with Disabilities at NIPS (AMD), December 2009 (talk)

Abstract

Brain-computer interfaces (BCI) aim to be the ultimate in assistive technology: decoding a user‘s intentions directly from brain signals without involving any muscles or peripheral nerves. Thus, some classes of BCI potentially offer hope for users with even the most extreme cases of paralysis, such as in late-stage Amyotrophic Lateral Sclerosis, where nothing else currently allows communication of any kind. Other lines in BCI research aim to restore lost motor function in as natural a way as possible, reconnecting and in some cases re-training motor-cortical areas to control prosthetic, or previously paretic, limbs. Research and development are progressing on both invasive and non-invasive fronts, although BCI has yet to make a breakthrough to widespread clinical application. The high-noise high-dimensional nature of brain-signals, particularly in non-invasive approaches and in patient populations, make robust decoding techniques a necessity. Generally, the approach has been to use relatively simple feature extraction techniques, such as template matching and band-power estimation, coupled to simple linear classifiers. This has led to a prevailing view among applied BCI researchers that (sophisticated) machine-learning is irrelevant since "it doesn‘t matter what classifier you use once you‘ve done your preprocessing right and extracted the right features." I shall show a few examples of how this runs counter to both the empirical reality and the spirit of what needs to be done to bring BCI into clinical application. Along the way I‘ll highlight some of the interesting problems that remain open for machine-learners.

PDF Web Web [BibTex]

2009

Hill, NJ. Machine Learning for Brain-Computer Interfaces Mini-Symposia on Assistive Machine Learning for People with Disabilities at NIPS (AMD), December 2009 (talk)

PDF Web Web [BibTex]

PAC-Bayesian Approach to Formulation of Clustering Objectives

Seldin, Y.

NIPS Workshop on "Clustering: Science or Art? Towards Principled Approaches", December 2009 (talk)

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 Web [BibTex]

Seldin, Y. PAC-Bayesian Approach to Formulation of Clustering Objectives NIPS Workshop on "Clustering: Science or Art? Towards Principled Approaches", December 2009 (talk)

PDF Web Web [BibTex]

Semi-supervised Kernel Canonical Correlation Analysis of Human Functional Magnetic Resonance Imaging Data

Shelton, JA.

Women in Machine Learning Workshop (WiML), December 2009 (talk)

Abstract

Kernel Canonical Correlation Analysis (KCCA) is a general technique for subspace learning that incorporates principal components analysis (PCA) and Fisher linear discriminant analysis (LDA) as special cases. By finding directions that maximize correlation, KCCA learns representations tied more closely to underlying process generating the the data and can ignore high-variance noise directions. However, for data where acquisition in a given modality is expensive or otherwise limited, KCCA may suffer from small sample effects. We propose to use semi-supervised Laplacian regularization to utilize data that are present in only one modality. This manifold learning approach is able to find highly correlated directions that also lie along the data manifold, resulting in a more robust estimate of correlated subspaces. Functional magnetic resonance imaging (fMRI) acquired data are naturally amenable to subspace techniques as data are well aligned and such data of the human brain are a particularly interesting candidate. In this study we implemented various supervised and semi-supervised versions of KCCA on human fMRI data, with regression to single and multivariate labels (corresponding to video content subjects viewed during the image acquisition). In each variate condition, Laplacian regularization improved performance whereas the semi-supervised variants of KCCA yielded the best performance. We additionally analyze the weights learned by the regression in order to infer brain regions that are important during different types of visual processing.

PDF Web [BibTex]

Shelton, JA. Semi-supervised Kernel Canonical Correlation Analysis of Human Functional Magnetic Resonance Imaging Data Women in Machine Learning Workshop (WiML), December 2009 (talk)

PDF Web [BibTex]

Event-Related Potentials in Brain-Computer Interfacing

Hill, NJ.

Invited lecture on the bachelor & masters course "Introduction to Brain-Computer Interfacing", October 2009 (talk)

Abstract

An introduction to event-related potentials with specific reference to their use in brain-computer interfacing applications and research.

PDF [BibTex]

Hill, NJ. Event-Related Potentials in Brain-Computer Interfacing Invited lecture on the bachelor & masters course "Introduction to Brain-Computer Interfacing", October 2009 (talk)

PDF [BibTex]

BCI2000 and Python

Hill, NJ.

Invited lecture at the 5th International BCI2000 Workshop, October 2009 (talk)

Abstract

A tutorial, with exercises, on how to integrate your own Python code with the BCI2000 software package.

PDF [BibTex]

Hill, NJ. BCI2000 and Python Invited lecture at the 5th International BCI2000 Workshop, October 2009 (talk)

PDF [BibTex]

Implementing a Signal Processing Filter in BCI2000 Using C++

Hill, NJ., Mellinger, J.

Invited lecture at the 5th International BCI2000 Workshop, October 2009 (talk)

Abstract

This tutorial shows how the functionality of the BCI2000 software package can be extended with one‘s own code, using BCI2000‘s C++ API.

PDF [BibTex]

Hill, NJ., Mellinger, J. Implementing a Signal Processing Filter in BCI2000 Using C++ Invited lecture at the 5th International BCI2000 Workshop, October 2009 (talk)

PDF [BibTex]

Randomized algorithms for statistical image analysis based on percolation theory

Davies, P., Langovoy, M., Wittich, O.

27th European Meeting of Statisticians (EMS), July 2009 (talk)

Abstract

We propose a novel probabilistic method for detection of signals and reconstruction of images in the presence of random noise. The method uses results from percolation and random graph theories (see Grimmett (1999)). We address the problem of detection and estimation of signals in situations where the signal-to-noise ratio is particularly low. We present an algorithm that allows to detect objects of various shapes in noisy images. The algorithm has linear complexity and exponential accuracy. Our algorithm substantially diers from wavelets-based algorithms (see Arias-Castro et.al. (2005)). Moreover, we present an algorithm that produces a crude estimate of an object based on the noisy picture. This algorithm also has linear complexity and is appropriate for real-time systems. We prove results on consistency and algorithmic complexity of our procedures.

Web PDF [BibTex]

Davies, P., Langovoy, M., Wittich, O. Randomized algorithms for statistical image analysis based on percolation theory 27th European Meeting of Statisticians (EMS), July 2009 (talk)

Web PDF [BibTex]

Learning Motor Primitives for Robotics

Kober, J., Peters, J., Oztop, E.

Advanced Telecommunications Research Center ATR, June 2009 (talk)

Abstract

The acquisition and self-improvement of novel motor skills is among the most important problems in robotics. Motor primitives offer one of the most promising frameworks for the application of machine learning techniques in this context. Employing the Dynamic Systems Motor primitives originally introduced by Ijspeert et al. (2003), appropriate learning algorithms for a concerted approach of both imitation and reinforcement learning are presented. Using these algorithms new motor skills, i.e., Ball-in-a-Cup, Ball-Paddling and Dart-Throwing, are learned.

[BibTex]

Kober, J., Peters, J., Oztop, E. Learning Motor Primitives for Robotics Advanced Telecommunications Research Center ATR, June 2009 (talk)

[BibTex]

Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer

Lampert, C.

IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June 2009 (talk)

Web [BibTex]

Lampert, C. Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June 2009 (talk)

Web [BibTex]

2006

A Kernel Method for the Two-Sample-Problem

Gretton, A., Borgwardt, K., Rasch, M., Schölkopf, B., Smola, A.

20th Annual Conference on Neural Information Processing Systems (NIPS), December 2006 (talk)

Abstract

We propose two statistical tests to determine if two samples are from different distributions. Our test statistic is in both cases the distance between the means of the two samples mapped into a reproducing kernel Hilbert space (RKHS). The first test is based on a large deviation bound for the test statistic, while the second is based on the asymptotic distribution of this statistic. We show that the test statistic can be computed in $O(m^2)$ time. We apply our approach to a variety of problems, including attribute matching for databases using the Hungarian marriage method, where our test performs strongly. We also demonstrate excellent performance when comparing distributions over graphs, for which no alternative tests currently exist.

PDF [BibTex]

2006

Gretton, A., Borgwardt, K., Rasch, M., Schölkopf, B., Smola, A. A Kernel Method for the Two-Sample-Problem 20th Annual Conference on Neural Information Processing Systems (NIPS), December 2006 (talk)

PDF [BibTex]

Ab-initio gene finding using machine learning

Schweikert, G., Zeller, G., Zien, A., Ong, C., de Bona, F., Sonnenburg, S., Phillips, P., Rätsch, G.

NIPS Workshop on New Problems and Methods in Computational Biology, December 2006 (talk)

Web [BibTex]

Schweikert, G., Zeller, G., Zien, A., Ong, C., de Bona, F., Sonnenburg, S., Phillips, P., Rätsch, G. Ab-initio gene finding using machine learning NIPS Workshop on New Problems and Methods in Computational Biology, December 2006 (talk)

Web [BibTex]

Reinforcement Learning by Reward-Weighted Regression

Peters, J.

NIPS Workshop: Towards a New Reinforcement Learning? , December 2006 (talk)

Web [BibTex]

Peters, J. Reinforcement Learning by Reward-Weighted Regression NIPS Workshop: Towards a New Reinforcement Learning? , December 2006 (talk)

Web [BibTex]

Graph boosting for molecular QSAR analysis

Saigo, H., Kadowaki, T., Kudo, T., Tsuda, K.

NIPS Workshop on New Problems and Methods in Computational Biology, December 2006 (talk)

Abstract

We propose a new boosting method that systematically combines graph mining and mathematical programming-based machine learning. Informative and interpretable subgraph features are greedily found by a series of graph mining calls. Due to our mathematical programming formulation, subgraph features and pre-calculated real-valued features are seemlessly integrated. We tested our algorithm on a quantitative structure-activity relationship (QSAR) problem, which is basically a regression problem when given a set of chemical compounds. In benchmark experiments, the prediction accuracy of our method favorably compared with the best results reported on each dataset.

Web [BibTex]

Saigo, H., Kadowaki, T., Kudo, T., Tsuda, K. Graph boosting for molecular QSAR analysis NIPS Workshop on New Problems and Methods in Computational Biology, December 2006 (talk)

Web [BibTex]

Inferring Causal Directions by Evaluating the Complexity of Conditional Distributions

Sun, X., Janzing, D., Schölkopf, B.

NIPS Workshop on Causality and Feature Selection, December 2006 (talk)

Abstract

We propose a new approach to infer the causal structure that has generated the observed statistical dependences among n random variables. The idea is that the factorization of the joint measure of cause and effect into P(cause)P(effect|cause) leads typically to simpler conditionals than non-causal factorizations. To evaluate the complexity of the conditionals we have tried two methods. First, we have compared them to those which maximize the conditional entropy subject to the observed first and second moments since we consider the latter as the simplest conditionals. Second, we have fitted the data with conditional probability measures being exponents of functions in an RKHS space and defined the complexity by a Hilbert-space semi-norm. Such a complexity measure has several properties that are useful for our purpose. We describe some encouraging results with both methods applied to real-world data. Moreover, we have combined constraint-based approaches to causal discovery (i.e., methods using only information on conditional statistical dependences) with our method in order to distinguish between causal hypotheses which are equivalent with respect to the imposed independences. Furthermore, we compare the performance to Bayesian approaches to causal inference.

Web [BibTex]

Sun, X., Janzing, D., Schölkopf, B. Inferring Causal Directions by Evaluating the Complexity of Conditional Distributions NIPS Workshop on Causality and Feature Selection, December 2006 (talk)

Web [BibTex]

Learning Optimal EEG Features Across Time, Frequency and Space

Farquhar, J., Hill, J., Schölkopf, B.

NIPS Workshop on Current Trends in Brain-Computer Interfacing, December 2006 (talk)

PDF Web [BibTex]

Farquhar, J., Hill, J., Schölkopf, B. Learning Optimal EEG Features Across Time, Frequency and Space NIPS Workshop on Current Trends in Brain-Computer Interfacing, December 2006 (talk)

PDF Web [BibTex]

Semi-Supervised Learning

Zien, A.

Advanced Methods in Sequence Analysis Lectures, November 2006 (talk)

Web [BibTex]

Zien, A. Semi-Supervised Learning Advanced Methods in Sequence Analysis Lectures, November 2006 (talk)

Web [BibTex]

A Machine Learning Approach for Determining the PET Attenuation Map from Magnetic Resonance Images

Hofmann, M., Steinke, F., Judenhofer, M., Claussen, C., Schölkopf, B., Pichler, B.

IEEE Medical Imaging Conference, November 2006 (talk)

Abstract

A promising new combination in multimodality imaging is MR-PET, where the high soft tissue contrast of Magnetic Resonance Imaging (MRI) and the functional information of Positron Emission Tomography (PET) are combined. Although many technical problems have recently been solved, it is still an open problem to determine the attenuation map from the available MR scan, as the MR intensities are not directly related to the attenuation values. One standard approach is an atlas registration where the atlas MR image is aligned with the patient MR thus also yielding an attenuation image for the patient. We also propose another approach, which to our knowledge has not been tried before: Using Support Vector Machines we predict the attenuation value directly from the local image information. We train this well-established machine learning algorithm using small image patches. Although both approaches sometimes yielded acceptable results, they also showed their specific shortcomings: The registration often fails with large deformations whereas the prediction approach is problematic when the local image structure is not characteristic enough. However, the failures often do not coincide and integration of both information sources is promising. We therefore developed a combination method extending Support Vector Machines to use not only local image structure but also atlas registered coordinates. We demonstrate the strength of this combination approach on a number of examples.

[BibTex]

Hofmann, M., Steinke, F., Judenhofer, M., Claussen, C., Schölkopf, B., Pichler, B. A Machine Learning Approach for Determining the PET Attenuation Map from Magnetic Resonance Images IEEE Medical Imaging Conference, November 2006 (talk)

[BibTex]

Semi-Supervised Support Vector Machines and Application to Spam Filtering

Zien, A.

ECML Discovery Challenge Workshop, September 2006 (talk)

Abstract

After introducing the semi-supervised support vector machine (aka TSVM for "transductive SVM"), a few popular training strategies are briefly presented. Then the assumptions underlying semi-supervised learning are reviewed. Finally, two modern TSVM optimization techniques are applied to the spam filtering data sets of the workshop; it is shown that they can achieve excellent results, if the problem of the data being non-iid can be handled properly.

PDF Web [BibTex]

Zien, A. Semi-Supervised Support Vector Machines and Application to Spam Filtering ECML Discovery Challenge Workshop, September 2006 (talk)

PDF Web [BibTex]

Inferential Structure Determination: Probabilistic determination and validation of NMR structures

Habeck, M.

Gordon Research Conference on Computational Aspects of Biomolecular NMR, September 2006 (talk)

Web [BibTex]

Habeck, M. Inferential Structure Determination: Probabilistic determination and validation of NMR structures Gordon Research Conference on Computational Aspects of Biomolecular NMR, September 2006 (talk)

Web [BibTex]

Machine Learning Algorithms for Polymorphism Detection

Schweikert, G., Zeller, G., Clark, R., Ossowski, S., Warthmann, N., Shinn, P., Frazer, K., Ecker, J., Huson, D., Weigel, D., Schölkopf, B., Rätsch, G.

2nd ISCB Student Council Symposium, August 2006 (talk)

Abstract

Analyzing resequencing array data using machine learning, we obtain a genome-wide inventory of polymorphisms in 20 wild strains of Arabidopsis thaliana, including 750,000 single nucleotide poly- morphisms (SNPs) and thousands of highly polymorphic regions and deletions. We thus provide an unprecedented resource for the study of natural variation in plants.

Web [BibTex]

Schweikert, G., Zeller, G., Clark, R., Ossowski, S., Warthmann, N., Shinn, P., Frazer, K., Ecker, J., Huson, D., Weigel, D., Schölkopf, B., Rätsch, G. Machine Learning Algorithms for Polymorphism Detection 2nd ISCB Student Council Symposium, August 2006 (talk)

Web [BibTex]

Inferential structure determination: Overview and new developments

Habeck, M.

Sixth CCPN Annual Conference: Efficient and Rapid Structure Determination by NMR, July 2006 (talk)

Web [BibTex]

Habeck, M. Inferential structure determination: Overview and new developments Sixth CCPN Annual Conference: Efficient and Rapid Structure Determination by NMR, July 2006 (talk)

Web [BibTex]

MCMC inference in (Conditionally) Conjugate Dirichlet Process Gaussian Mixture Models

Rasmussen, C., Görür, D.

ICML Workshop on Learning with Nonparametric Bayesian Methods, June 2006 (talk)

Abstract

We compare the predictive accuracy of the Dirichlet Process Gaussian mixture models using conjugate and conditionally conjugate priors and show that better density models result from using the wider class of priors. We explore several MCMC schemes exploiting conditional conjugacy and show their computational merits on several multidimensional density estimation problems.

Web [BibTex]

Rasmussen, C., Görür, D. MCMC inference in (Conditionally) Conjugate Dirichlet Process Gaussian Mixture Models ICML Workshop on Learning with Nonparametric Bayesian Methods, June 2006 (talk)

Web [BibTex]

Sampling for non-conjugate infinite latent feature models

Görür, D., Rasmussen, C.

(Editors: Bernardo, J. M.), 8th Valencia International Meeting on Bayesian Statistics (ISBA), June 2006 (talk)

Abstract

Latent variable models are powerful tools to model the underlying structure in data. Infinite latent variable models can be defined using Bayesian nonparametrics. Dirichlet process (DP) models constitute an example of infinite latent class models in which each object is assumed to belong to one of the, mutually exclusive, infinitely many classes. Recently, the Indian buffet process (IBP) has been defined as an extension of the DP. IBP is a distribution over sparse binary matrices with infinitely many columns which can be used as a distribution for non-exclusive features. Inference using Markov chain Monte Carlo (MCMC) in conjugate IBP models has been previously described, however requiring conjugacy restricts the use of IBP. We describe an MCMC algorithm for non-conjugate IBP models. Modelling the choice behaviour is an important topic in psychology, economics and related fields. Elimination by Aspects (EBA) is a choice model that assumes each alternative has latent features with associated weights that lead to the observed choice outcomes. We formulate a non-parametric version of EBA by using IBP as the prior over the latent binary features. We infer the features of objects that lead to the choice data by using our sampling scheme for inference.

PDF [BibTex]

Görür, D., Rasmussen, C. Sampling for non-conjugate infinite latent feature models (Editors: Bernardo, J. M.), 8th Valencia International Meeting on Bayesian Statistics (ISBA), June 2006 (talk)

PDF [BibTex]

An Inventory of Sequence Polymorphisms For Arabidopsis

Clark, R., Ossowski, S., Schweikert, G., Rätsch, G., Shinn, P., Zeller, G., Warthmann, N., Fu, G., Hinds, D., Chen, H., Frazer, K., Huson, D., Schölkopf, B., Nordborg, M., Ecker, J., Weigel, D.

17th International Conference on Arabidopsis Research, April 2006 (talk)

Abstract

We have used high-density oligonucleotide arrays to characterize common sequence variation in 20 wild strains of Arabidopsis thaliana that were chosen for maximal genetic diversity. Both strands of each possible SNP of the 119 Mb reference genome were represented on the arrays, which were hybridized with whole genome, isothermally amplified DNA to minimize ascertainment biases. Using two complementary approaches, a model based algorithm, and a newly developed machine learning method, we identified over 550,000 SNPs with a false discovery rate of ~ 0.03 (average of 1 SNP for every 216 bp of the genome). A heuristic algorithm predicted in addition ~700 highly polymorphic or deleted regions per accession. Over 700 predicted polymorphisms with major functional effects (e.g., premature stop codons, or deletions of coding sequence) were validated by dideoxy sequencing. Using this data set, we provide the first systematic description of the types of genes that harbor major effect polymorphisms in natural populations at moderate allele frequencies. The data also provide an unprecedented resource for the study of genetic variation in an experimentally tractable, multicellular model organism.

[BibTex]

Clark, R., Ossowski, S., Schweikert, G., Rätsch, G., Shinn, P., Zeller, G., Warthmann, N., Fu, G., Hinds, D., Chen, H., Frazer, K., Huson, D., Schölkopf, B., Nordborg, M., Ecker, J., Weigel, D. An Inventory of Sequence Polymorphisms For Arabidopsis 17th International Conference on Arabidopsis Research, April 2006 (talk)

[BibTex]

Machine Learning and Applications in Biology

Shin, H.

6th Course in Bioinformatics for Molecular Biologist, March 2006 (talk)

Abstract

The emergence of the fields of computational biology and bioinformatics has alleviated the burden of solving many biological problems, saving the time and cost required for experiments and also providing predictions that guide new experiments. Within computational biology, machine learning algorithms have played a central role in dealing with the flood of biological data. The goal of this tutorial is to raise awareness and comprehension of machine learning so that biologists can properly match the task at hand to the corresponding analytical approach. We start by categorizing biological problem settings and introduce the general machine learning schemes that fit best to each or these categories. We then explore representative models in further detail, from traditional statistical models to recent kernel models, presenting several up-to-date research projects in bioinfomatics to exemplify how biological questions can benefit from a machine learning approach. Finally, we discuss how cooperation between biologists and machine learners might be made smoother.

PDF [BibTex]

Shin, H. Machine Learning and Applications in Biology 6th Course in Bioinformatics for Molecular Biologist, March 2006 (talk)

PDF [BibTex]

2003

Learning Control and Planning from the View of Control Theory and Imitation

Peters, J., Schaal, S.

NIPS Workshop "Planning for the Real World: The promises and challenges of dealing with uncertainty", December 2003 (talk)

Abstract

Learning control and planning in high dimensional continuous state-action systems, e.g., as needed in a humanoid robot, has so far been a domain beyond the applicability of generic planning techniques like reinforcement learning and dynamic programming. This talk describes an approach we have taken in order to enable complex robotics systems to learn to accomplish control tasks. Adaptive learning controllers equipped with statistical learning techniques can be used to learn tracking controllers -- missing state information and uncertainty in the state estimates are usually addressed by observers or direct adaptive control methods. Imitation learning is used as an ingredient to seed initial control policies whose output is a desired trajectory suitable to accomplish the task at hand. Reinforcement learning with stochastic policy gradients using a natural gradient forms the third component that allows refining the initial control policy until the task is accomplished. In comparison to general learning control, this approach is highly prestructured and thus more domain specific. However, it seems to be a theoretically clean and feasible strategy for control systems of the complexity that we need to address.

Web [BibTex]

2003

Peters, J., Schaal, S. Learning Control and Planning from the View of Control Theory and Imitation NIPS Workshop "Planning for the Real World: The promises and challenges of dealing with uncertainty", December 2003 (talk)

Web [BibTex]

Recurrent neural networks from learning attractor dynamics

Schaal, S., Peters, J.

NIPS Workshop on RNNaissance: Recurrent Neural Networks, December 2003 (talk)

Abstract

Many forms of recurrent neural networks can be understood in terms of dynamic systems theory of difference equations or differential equations. Learning in such systems corresponds to adjusting some internal parameters to obtain a desired time evolution of the network, which can usually be characterized in term of point attractor dynamics, limit cycle dynamics, or, in some more rare cases, as strange attractor or chaotic dynamics. Finding a stable learning process to adjust the open parameters of the network towards shaping the desired attractor type and basin of attraction has remain a complex task, as the parameter trajectories during learning can lead the system through a variety of undesirable unstable behaviors, such that learning may never succeed. In this presentation, we review a recently developed learning framework for a class of recurrent neural networks that employs a more structured network approach. We assume that the canonical system behavior is known a priori, e.g., it is a point attractor or a limit cycle. With either supervised learning or reinforcement learning, it is possible to acquire the transformation from a simple representative of this canonical behavior (e.g., a 2nd order linear point attractor, or a simple limit cycle oscillator) to the desired highly complex attractor form. For supervised learning, one shot learning based on locally weighted regression techniques is possible. For reinforcement learning, stochastic policy gradient techniques can be employed. In any case, the recurrent network learned by these methods inherits the stability properties of the simple dynamic system that underlies the nonlinear transformation, such that stability of the learning approach is not a problem. We demonstrate the success of this approach for learning various skills on a humanoid robot, including tasks that require to incorporate additional sensory signals as coupling terms to modify the recurrent network evolution on-line.

Web [BibTex]

Schaal, S., Peters, J. Recurrent neural networks from learning attractor dynamics NIPS Workshop on RNNaissance: Recurrent Neural Networks, December 2003 (talk)

Web [BibTex]

Statistical Learning Theory

Bousquet, O.

Machine Learning Summer School, August 2003 (talk)

PDF [BibTex]

Bousquet, O. Statistical Learning Theory Machine Learning Summer School, August 2003 (talk)

PDF [BibTex]

Remarks on Statistical Learning Theory

Bousquet, O.

Machine Learning Summer School, August 2003 (talk)

PDF [BibTex]

Bousquet, O. Remarks on Statistical Learning Theory Machine Learning Summer School, August 2003 (talk)

PDF [BibTex]

Rademacher and Gaussian averages in Learning Theory

Bousquet, O.

Universite de Marne-la-Vallee, March 2003 (talk)

PDF [BibTex]

Bousquet, O. Rademacher and Gaussian averages in Learning Theory Universite de Marne-la-Vallee, March 2003 (talk)

PDF [BibTex]

Statistical Learning Theory

Bousquet, O., Schölkopf, B.

March 2003 (talk)

PDF [BibTex]

Bousquet, O., Schölkopf, B. Statistical Learning Theory March 2003 (talk)

PDF [BibTex]

Concentration Inequalities and Data-Dependent Error Bounds

Bousquet, O.

Uni. Jena, February 2003 (talk)

PDF [BibTex]

Bousquet, O. Concentration Inequalities and Data-Dependent Error Bounds Uni. Jena, February 2003 (talk)

PDF [BibTex]

Introduction: Robots with Cognition?

Franz, MO.

6, pages: 38, (Editors: H.H. Bülthoff, K.R. Gegenfurtner, H.A. Mallot, R. Ulrich, F.A. Wichmann), 6. T{\"u}binger Wahrnehmungskonferenz (TWK), February 2003 (talk)

Abstract

Using robots as models of cognitive behaviour has a long tradition in robotics. Parallel to the historical development in cognitive science, one observes two major, subsequent waves in cognitive robotics. The first is based on ideas of classical, cognitivist Artificial Intelligence (AI). According to the AI view of cognition as rule-based symbol manipulation, these robots typically try to extract symbolic descriptions of the environment from their sensors that are used to update a common, global world representation from which, in turn, the next action of the robot is derived. The AI approach has been successful in strongly restricted and controlled environments requiring well-defined tasks, e.g. in industrial assembly lines. AI-based robots mostly failed, however, in the unpredictable and unstructured environments that have to be faced by mobile robots. This has provoked the second wave in cognitive robotics which tries to achieve cognitive behaviour as an emergent property from the interaction of simple, low-level modules. Robots of the second wave are called animats as their architecture is designed to closely model aspects of real animals. Using only simple reactive mechanisms and Hebbian-type or evolutionary learning, the resulting animats often outperformed the highly complex AI-based robots in tasks such as obstacle avoidance, corridor following etc. While successful in generating robust, insect-like behaviour, typical animats are limited to stereotyped, fixed stimulus-response associations. If one adopts the view that cognition requires a flexible, goal-dependent choice of behaviours and planning capabilities (H.A. Mallot, Kognitionswissenschaft, 1999, 40-48) then it appears that cognitive behaviour cannot emerge from a collection of purely reactive modules. It rather requires environmentally decoupled structures that work without directly engaging the actions that it is concerned with. This poses the current challenge to cognitive robotics: How can we build cognitive robots that show the robustness and the learning capabilities of animats without falling back into the representational paradigm of AI? The speakers of the symposium present their approaches to this question in the context of robot navigation and sensorimotor learning. In the first talk, Prof. Helge Ritter introduces a robot system for imitation learning capable of exploring various alternatives in simulation before actually performing a task. The second speaker, Angelo Arleo, develops a model of spatial memory in rat navigation based on his electrophysiological experiments. He validates the model on a mobile robot which, in some navigation tasks, shows a performance comparable to that of the real rat. A similar model of spatial memory is used to investigate the mechanisms of territory formation in a series of robot experiments presented by Prof. Hanspeter Mallot. In the last talk, we return to the domain of sensorimotor learning where Ralf M{\"o}ller introduces his approach to generate anticipatory behaviour by learning forward models of sensorimotor relationships.

Web [BibTex]

Franz, MO. Introduction: Robots with Cognition? 6, pages: 38, (Editors: H.H. Bülthoff, K.R. Gegenfurtner, H.A. Mallot, R. Ulrich, F.A. Wichmann), 6. T{\"u}binger Wahrnehmungskonferenz (TWK), February 2003 (talk)

Web [BibTex]