Header logo is ei


2007


no image
Neighborhood Property based Pattern Selection for Support Vector Machines

Shin, H., Cho, S.

Neural Computation, 19(3):816-855, March 2007 (article)

Abstract
The support vector machine (SVM) has been spotlighted in the machine learning community because of its theoretical soundness and practical performance. When applied to a large data set, however, it requires a large memory and a long time for training. To cope with the practical difficulty, we propose a pattern selection algorithm based on neighborhood properties. The idea is to select only the patterns that are likely to be located near the decision boundary. Those patterns are expected to be more informative than the randomly selected patterns. The experimental results provide promising evidence that it is possible to successfully employ the proposed algorithm ahead of SVM training.

PDF Web DOI [BibTex]

2007

PDF Web DOI [BibTex]


no image
Training a Support Vector Machine in the Primal

Chapelle, O.

Neural Computation, 19(5):1155-1178, March 2007 (article)

Abstract
Most literature on Support Vector Machines (SVMs) concentrate on the dual optimization problem. In this paper, we would like to point out that the primal problem can also be solved efficiently, both for linear and non-linear SVMs, and that there is no reason for ignoring this possibilty. On the contrary, from the primal point of view new families of algorithms for large scale SVM training can be investigated.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Dirichlet Mixtures of Bayesian Linear Gaussian State-Space Models: a Variational Approach

Chiappa, S., Barber, D.

(161), Max Planck Institute for Biological Cybernetics, Tübingen, Germany, March 2007 (techreport)

Abstract
We describe two related models to cluster multidimensional time-series under the assumption of an underlying linear Gaussian dynamical process. In the first model, times-series are assigned to the same cluster when they show global similarity in their dynamics, while in the second model times-series are assigned to the same cluster when they show simultaneous similarity. Both models are based on Dirichlet Mixtures of Bayesian Linear Gaussian State-Space Models in order to (semi) automatically determine an appropriate number of components in the mixture, and to additionally bias the components to a parsimonious parameterization. The resulting models are formally intractable and to deal with this we describe a deterministic approximation based on a novel implementation of Variational Bayes.

PDF [BibTex]

PDF [BibTex]


no image
3D Reconstruction of Neural Circuits from Serial EM Images

Maack, N., Kapfer, C., Macke, J., Schölkopf, B., Denk, W., Borst, A.

31st G{\"o}ttingen Neurobiology Conference, 31, pages: 1195, March 2007 (poster)

PDF [BibTex]

PDF [BibTex]


no image
Transductive Classification via Local Learning Regularization

Wu, M., Schölkopf, B.

In JMLR Workshop and Conference Proceedings Volume 2: AISTATS 2007, pages: 628-635, (Editors: M Meila and X Shen), 11th International Conference on Artificial Intelligence and Statistics, March 2007 (inproceedings)

Abstract
The idea of local learning, classifying a particular point based on its neighbors, has been successfully applied to supervised learning problems. In this paper, we adapt it for Transductive Classification (TC) problems. Specifically, we formulate a Local Learning Regularizer (LL-Reg) which leads to a solution with the property that the label of each data point can be well predicted based on its neighbors and their labels. For model selection, an efficient way to compute the leave-one-out classification error is provided for the proposed and related algorithms. Experimental results using several benchmark datasets illustrate the effectiveness of the proposed approach.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Identifying temporal population codes in the retina using canonical correlation analysis

Bethge, M., Macke, J., Gerwinn, S., Zeck, G.

31st G{\"o}ttingen Neurobiology Conference, 31, pages: 359, March 2007 (poster)

PDF PDF [BibTex]

PDF PDF [BibTex]


no image
Bayesian Neural System identification: error bars, receptive fields and neural couplings

Gerwinn, S., Seeger, M., Zeck, G., Bethge, M.

31st G{\"o}ttingen Neurobiology Conference, 31, pages: 360, March 2007 (poster)

PDF PDF [BibTex]

PDF PDF [BibTex]


no image
Applications of Kernel Machines to Structured Data

Eichhorn, J.

Biologische Kybernetik, Technische Universität Berlin, Berlin, Germany, March 2007, passed with "sehr gut", published online (phdthesis)

PDF [BibTex]

PDF [BibTex]


no image
A priori Knowledge from Non-Examples

Sinz, FH.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, March 2007 (diplomathesis)

PDF Web [BibTex]

PDF Web [BibTex]


no image
Improving the Caenorhabditis elegans Genome Annotation Using Machine Learning

Rätsch, G., Sonnenburg, S., Srinivasan, J., Witte, H., Müller, K., Sommer, R., Schölkopf, B.

PLoS Computational Biology, 3(2, e20):0313-0322, February 2007 (article)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
The Independent Components of Natural Images are Perceptually Dependent

Bethge, M., Wiecki, T., Wichmann, F.

In Human Vision and Electronic Imaging XII, pages: 1-12, (Editors: Rogowitz, B. E.), SPIE, Bellingham, WA, USA, SPIE Human Vision and Electronic Imaging Conference, February 2007 (inproceedings)

Abstract
The independent components of natural images are a set of linear filters which are optimized for statistical independence. With such a set of filters images can be represented without loss of information. Intriguingly, the filter shapes are localized, oriented, and bandpass, resembling important properties of V1 simple cell receptive fields. Here we address the question of whether the independent components of natural images are also perceptually less dependent than other image components. We compared the pixel basis, the ICA basis and the discrete cosine basis by asking subjects to interactively predict missing pixels (for the pixel basis) or to predict the coefficients of ICA and DCT basis functions in patches of natural images. Like Kersten (1987) we find the pixel basis to be perceptually highly redundant but perhaps surprisingly, the ICA basis showed significantly higher perceptual dependencies than the DCT basis. This shows a dissociation between statistical and perceptual dependence measures.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Modeling data using directional distributions: Part II

Sra, S., Jain, P., Dhillon, I.

(TR-07-05), University of Texas, Austin, TX, USA, February 2007 (techreport)

Abstract
High-dimensional data is central to most data mining applications, and only recently has it been modeled via directional distributions. In [Banerjee et al., 2003] the authors introduced the use of the von Mises-Fisher (vMF) distribution for modeling high-dimensional directional data, particularly for text and gene expression analysis. The vMF distribution is one of the simplest directional distributions. TheWatson, Bingham, and Fisher-Bingham distributions provide distri- butions with an increasing number of parameters and thereby commensurately increased modeling power. This report provides a followup study to the initial development in [Banerjee et al., 2003] by presenting Expectation Maximization (EM) procedures for estimating parameters of a mixture of Watson (moW) distributions. The numerical challenges associated with parameter estimation for both of these distributions are significantly more difficult than for the vMF distribution. We develop new numerical approximations for estimating the parameters permitting us to model real- life data more accurately. Our experimental results establish that for certain data sets improved modeling power translates into better results.

PDF [BibTex]

PDF [BibTex]


no image
About the Triangle Inequality in Perceptual Spaces

Jäkel, F., Schölkopf, B., Wichmann, F.

Proceedings of the Computational and Systems Neuroscience Meeting 2007 (COSYNE), 4, pages: 308, February 2007 (poster)

PDF Web [BibTex]

PDF Web [BibTex]


no image
Automatic 3D Face Reconstruction from Single Images or Video

Breuer, P., Kim, K., Kienzle, W., Blanz, V., Schölkopf, B.

(160), Max Planck Institute for Biological Cybernetics, Tübingen, Germany, February 2007 (techreport)

Abstract
This paper presents a fully automated algorithm for reconstructing a textured 3D model of a face from a single photograph or a raw video stream. The algorithm is based on a combination of Support Vector Machines (SVMs) and a Morphable Model of 3D faces. After SVM face detection, individual facial features are detected using a novel regression-and classification-based approach, and probabilistically plausible configurations of features are selected to produce a list of candidates for several facial feature positions. In the next step, the configurations of feature points are evaluated using a novel criterion that is based on a Morphable Model and a combination of linear projections. Finally, the feature points initialize a model-fitting procedure of the Morphable Model. The result is a high-resolution 3D surface model.

PDF [BibTex]

PDF [BibTex]


no image
Center-surround filters emerge from optimizing predictivity in a free-viewing task

Kienzle, W., Wichmann, F., Schölkopf, B., Franz, M.

Proceedings of the Computational and Systems Neuroscience Meeting 2007 (COSYNE), 4, pages: 207, February 2007 (poster)

PDF Web [BibTex]

PDF Web [BibTex]


no image
Nonlinear Receptive Field Analysis: Making Kernel Methods Interpretable

Kienzle, W., Macke, J., Wichmann, F., Schölkopf, B., Franz, M.

Computational and Systems Neuroscience Meeting 2007 (COSYNE 2007), 4, pages: 16, February 2007 (poster)

PDF Web [BibTex]

PDF Web [BibTex]


no image
Statistical Consistency of Kernel Canonical Correlation Analysis

Fukumizu, K., Bach, F., Gretton, A.

Journal of Machine Learning Research, 8, pages: 361-383, February 2007 (article)

Abstract
While kernel canonical correlation analysis (CCA) has been applied in many contexts, the convergence of finite sample estimates of the associated functions to their population counterparts has not yet been established. This paper gives a mathematical proof of the statistical convergence of kernel CCA, providing a theoretical justification for the method. The proof uses covariance operators defined on reproducing kernel Hilbert spaces, and analyzes the convergence of their empirical estimates of finite rank to their population counterparts, which can have infinite rank. The result also gives a sufficient condition for convergence on the regularization coefficient involved in kernel CCA: this should decrease as n^{-1/3}, where n is the number of data.

PDF [BibTex]

PDF [BibTex]


no image
Unsupervised learning of a steerable basis for invariant image representations

Bethge, M., Gerwinn, S., Macke, J.

In Human Vision and Electronic Imaging XII, pages: 1-12, (Editors: Rogowitz, B. E.), SPIE, Bellingham, WA, USA, SPIE Human Vision and Electronic Imaging Conference, February 2007 (inproceedings)

Abstract
There are two aspects to unsupervised learning of invariant representations of images: First, we can reduce the dimensionality of the representation by finding an optimal trade-off between temporal stability and informativeness. We show that the answer to this optimization problem is generally not unique so that there is still considerable freedom in choosing a suitable basis. Which of the many optimal representations should be selected? Here, we focus on this second aspect, and seek to find representations that are invariant under geometrical transformations occuring in sequences of natural images. We utilize ideas of steerability and Lie groups, which have been developed in the context of filter design. In particular, we show how an anti-symmetric version of canonical correlation analysis can be used to learn a full-rank image basis which is steerable with respect to rotations. We provide a geometric interpretation of this algorithm by showing that it finds the two-dimensional eigensubspaces of the avera ge bivector. For data which exhibits a variety of transformations, we develop a bivector clustering algorithm, which we use to learn a basis of generalized quadrature pairs (i.e. complex cells) from sequences of natural images.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Estimating Population Receptive Fields in Space and Time

Macke, J., Zeck, G., Bethge, M.

Computational and Systems Neuroscience Meeting 2007 (COSYNE 2007), 4, pages: 44, February 2007 (poster)

PDF Web [BibTex]

PDF Web [BibTex]


no image
Machine Learning for Mass Production and Industrial Engineering

Pfingsten, T.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, February 2007 (phdthesis)

PDF [BibTex]

PDF [BibTex]


no image
New Margin- and Evidence-Based Approaches for EEG Signal Classification

Hill, N., Farquhar, J.

Invited talk at the FaSor Jahressymposium, February 2007 (talk)

PDF [BibTex]

PDF [BibTex]


no image
On the Pre-Image Problem in Kernel Methods

BakIr, G., Schölkopf, B., Weston, J.

In Kernel Methods in Bioengineering, Signal and Image Processing, pages: 284-302, (Editors: G Camps-Valls and JL Rojo-Álvarez and M Martínez-Ramón), Idea Group Publishing, Hershey, PA, USA, January 2007 (inbook)

Abstract
In this chapter we are concerned with the problem of reconstructing patterns from their representation in feature space, known as the pre-image problem. We review existing algorithms and propose a learning based approach. All algorithms are discussed regarding their usability and complexity and evaluated on an image denoising application.

DOI [BibTex]

DOI [BibTex]


no image
A Subspace Kernel for Nonlinear Feature Extraction

Wu, M., Farquhar, J.

In IJCAI-07, pages: 1125-1130, (Editors: Veloso, M. M.), AAAI Press, Menlo Park, CA, USA, International Joint Conference on Artificial Intelligence, January 2007 (inproceedings)

Abstract
Kernel based nonlinear Feature Extraction (KFE) or dimensionality reduction is a widely used pre-processing step in pattern classification and data mining tasks. Given a positive definite kernel function, it is well known that the input data are implicitly mapped to a feature space with usually very high dimensionality. The goal of KFE is to find a low dimensional subspace of this feature space, which retains most of the information needed for classification or data analysis. In this paper, we propose a subspace kernel based on which the feature extraction problem is transformed to a kernel parameter learning problem. The key observation is that when projecting data into a low dimensional subspace of the feature space, the parameters that are used for describing this subspace can be regarded as the parameters of the kernel function between the projected data. Therefore current kernel parameter learning methods can be adapted to optimize this parameterized kernel function. Experimental results are provided to validate the effectiveness of the proposed approach.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Graph kernels for disease outcome prediction from protein-protein interaction networks

Borgwardt, KM., Vishwanathan, SVN., Schraudolph, N., Kriegel, H-P.

In pages: 4-15, (Editors: Altman, R.B. A.K. Dunker, L. Hunter, T. Murray, T.E. Klein), World Scientific, Hackensack, NJ, USA, Pacific Symposium on Biocomputing (PSB), January 2007 (inproceedings)

Abstract
It is widely believed that comparing discrepancies in the protein-protein interaction (PPI) networks of individuals will become an important tool in understanding and preventing diseases. Currently PPI networks for individuals are not available, but gene expression data is becoming easier to obtain and allows us to represent individuals by a co-integrated gene expression/protein interaction network. Two major problems hamper the application of graph kernels – state-of-the-art methods for whole-graph comparison – to compare PPI networks. First, these methods do not scale to graphs of the size of a PPI network. Second, missing edges in these interaction networks are biologically relevant for detecting discrepancies, yet, these methods do not take this into account. In this article we present graph kernels for biological network comparison that are fast to compute and take into account missing interactions. We evaluate their practical performance on two datasets of co-integrated gene expression/PPI networks.

PDF [BibTex]

PDF [BibTex]


no image
Some observations on the pedestal effect

Henning, G., Wichmann, F.

Journal of Vision, 7(1:3):1-15, January 2007 (article)

Abstract
The pedestal or dipper effect is the large improvement in the detectability of a sinusoidal grating observed when it is added to a masking or pedestal grating of the same spatial frequency, orientation, and phase. We measured the pedestal effect in both broadband and notched noiseVnoise from which a 1.5-octave band centered on the signal frequency had been removed. Although the pedestal effect persists in broadband noise, it almost disappears in the notched noise. Furthermore, the pedestal effect is substantial when either high- or low-pass masking noise is used. We conclude that the pedestal effect in the absence of notched noise results principally from the use of information derived from channels with peak sensitivities at spatial frequencies different from that of the signal and the pedestal. We speculate that the spatial-frequency components of the notched noise above and below the spatial frequency of the signal and the pedestal prevent ‘‘off-frequency looking,’’ that is, prevent the use of information about changes in contrast carried in channels tuned to spatial frequencies that are very much different from that of the signal and the pedestal. Thus, the pedestal or dipper effect measured without notched noise appears not to be a characteristic of individual spatial-frequency-tuned channels.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Development of a Brain-Computer Interface Approach Based on Covert Attention to Tactile Stimuli

Raths, C.

University of Tübingen, Germany, University of Tübingen, Germany, January 2007 (diplomathesis)

[BibTex]

[BibTex]


no image
Cue Combination and the Effect of Horizontal Disparity and Perspective on Stereoacuity

Zalevski, AM., Henning, GB., Hill, NJ.

Spatial Vision, 20(1):107-138, January 2007 (article)

Abstract
Relative depth judgments of vertical lines based on horizontal disparity deteriorate enormously when the lines form part of closed configurations (Westheimer, 1979). In studies showing this effect, perspective was not manipulated and thus produced inconsistency between horizontal disparity and perspective. We show that stereoacuity improves dramatically when perspective and horizontal disparity are made consistent. Observers appear to use unhelpful perspective cues in judging the relative depth of the vertical sides of rectangles in a way not incompatible with a form of cue weighting. However, 95% confidence intervals for the weights derived for cues usually exceed the a-priori [0-1] range.

PDF PDF DOI [BibTex]

PDF PDF DOI [BibTex]


no image
Independent Factor Reinforcement Learning for Portfolio Management

Li, J., Zhang, K., Chan, L.

In Proceedings of the 8th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2007), pages: 1020-1031, (Editors: H Yin and P Tiño and E Corchado and W Byrne and X Yao), Springer, Berlin, Germany, 8th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL), 2007 (inproceedings)

Web [BibTex]

Web [BibTex]


no image
A Machine Learning Approach for Estimating the Attenuation Map for a Combined PET/MR Scanner

Hofmann, M.

Biologische Kybernetik, Max-Planck Institute for Biological Cybernetics, Tübingen, Germany, 2007 (diplomathesis)

[BibTex]

[BibTex]


no image
Classificazione di immagini telerilevate satellitari per agricoltura di precisione

Arnoldi, E., Bruzzone, L., Carlin, L., Pedron, L., Persello, C.

MondoGis: Il Mondo dei Sistemi Informativi Geografici, 63, pages: 13-17, 2007 (article)

[BibTex]

[BibTex]


no image
Separating convolutive mixtures by pairwise mutual information minimization", IEEE Signal Processing Letters

Zhang, K., Chan, L.

IEEE Signal Processing Letters, 14(12):992-995, 2007 (article)

Abstract
Blind separation of convolutive mixtures by minimizing the mutual information between output sequences can avoid the side effect of temporally whitening the outputs, but it involves the score function difference, whose estimation may be problematic when the data dimension is greater than two. This greatly limits the application of this method. Fortunately, for separating convolutive mixtures, pairwise independence of outputs leads to their mutual independence. As an implementation of this idea, we propose a way to separate convolutive mixtures by enforcing pairwise independence. This approach can be applied to separate convolutive mixtures of a moderate number of sources.

Web [BibTex]


no image
Some comments on ν-SVM

Dinuzzo, F., De Nicolao, G.

In A tribute to Antonio Lepschy, pages: -, (Editors: Picci, G. , M. E. Valcher), Edizione Libreria Progetto, Padova, Italy, 2007 (inbook)

[BibTex]

[BibTex]


no image
Kernel-Based Nonlinear Independent Component Analysis

Zhang, K., Chan, L.

In Independent Component Analysis and Signal Separation, 7th International Conference, ICA 2007, pages: 301-308, (Editors: M E Davies and C J James and S A Abdallah and M D Plumbley), Springer, 7th International Conference on Independent Component Analysis and Signal Separation (ICA), 2007, Lecture Notes in Computer Science, Vol. 4666 (inproceedings)

Web DOI [BibTex]

Web DOI [BibTex]


no image
Mathematik der Wahrnehmung: Wendepunkte

Wichman, F., Ernst, MO.

Akademische Mitteilungen zw{\"o}lf: F{\"u}nf Sinne, pages: 32-37, 2007 (misc)

[BibTex]

[BibTex]


no image
Towards Machine Learning of Motor Skills

Peters, J., Schaal, S., Schölkopf, B.

In Proceedings of Autonome Mobile Systeme (AMS), pages: 138-144, (Editors: K Berns and T Luksch), 2007, clmc (inproceedings)

Abstract
Autonomous robots that can adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s, however, made it clear that an approach purely based on reasoning or human insights would not be able to model all the perceptuomotor tasks that a robot should fulfill. Instead, new hope was put in the growing wake of machine learning that promised fully adaptive control algorithms which learn both by observation and trial-and-error. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach to motor skill learning in order to get one step closer towards human-like performance. For doing so, we study two ma jor components for such an approach, i.e., firstly, a theoretically well-founded general approach to representing the required control structures for task representation and execution and, secondly, appropriate learning algorithms which can be applied in this setting.

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Reinforcement Learning for Optimal Control of Arm Movements

Theodorou, E., Peters, J., Schaal, S.

In Abstracts of the 37st Meeting of the Society of Neuroscience., Neuroscience, 2007, clmc (inproceedings)

Abstract
Every day motor behavior consists of a plethora of challenging motor skills from discrete movements such as reaching and throwing to rhythmic movements such as walking, drumming and running. How this plethora of motor skills can be learned remains an open question. In particular, is there any unifying computa-tional framework that could model the learning process of this variety of motor behaviors and at the same time be biologically plausible? In this work we aim to give an answer to these questions by providing a computational framework that unifies the learning mechanism of both rhythmic and discrete movements under optimization criteria, i.e., in a non-supervised trial-and-error fashion. Our suggested framework is based on Reinforcement Learning, which is mostly considered as too costly to be a plausible mechanism for learning com-plex limb movement. However, recent work on reinforcement learning with pol-icy gradients combined with parameterized movement primitives allows novel and more efficient algorithms. By using the representational power of such mo-tor primitives we show how rhythmic motor behaviors such as walking, squash-ing and drumming as well as discrete behaviors like reaching and grasping can be learned with biologically plausible algorithms. Using extensive simulations and by using different reward functions we provide results that support the hy-pothesis that Reinforcement Learning could be a viable candidate for motor learning of human motor behavior when other learning methods like supervised learning are not feasible.

[BibTex]

[BibTex]


no image
Machine Learning of Motor Skills for Robotics

Peters, J.

University of Southern California, Los Angeles, CA, USA, University of Southern California, Los Angeles, CA, USA, 2007, clmc (phdthesis)

Abstract
Autonomous robots that can assist humans in situations of daily life have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. A first step towards this goal is to create robots that can accomplish a multitude of different tasks, triggered by environmental context or higher level instruction. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s, however, made it clear that an approach purely based on reasoning and human insights would not be able to model all the perceptuomotor tasks that a robot should fulfill. Instead, new hope was put in the growing wake of machine learning that promised fully adaptive control algorithms which learn both by observation and trial-and-error. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this thesis, we investigate the ingredients for a general approach to motor skill learning in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, a theoretically well-founded general approach to representing the required control structures for task representation and execution and, secondly, appropriate learning algorithms which can be applied in this setting. As a theoretical foundation, we first study a general framework to generate control laws for real robots with a particular focus on skills represented as dynamical systems in differential constraint form. We present a point-wise optimal control framework resulting from a generalization of Gauss' principle and show how various well-known robot control laws can be derived by modifying the metric of the employed cost function. The framework has been successfully applied to task space tracking control for holonomic systems for several different metrics on the anthropomorphic SARCOS Master Arm. In order to overcome the limiting requirement of accurate robot models, we first employ learning methods to find learning controllers for task space control. However, when learning to execute a redundant control problem, we face the general problem of the non-convexity of the solution space which can force the robot to steer into physically impossible configurations if supervised learning methods are employed without further consideration. This problem can be resolved using two major insights, i.e., the learning problem can be treated as locally convex and the cost function of the analytical framework can be used to ensure global consistency. Thus, we derive an immediate reinforcement learning algorithm from the expectation-maximization point of view which leads to a reward-weighted regression technique. This method can be used both for operational space control as well as general immediate reward reinforcement learning problems. We demonstrate the feasibility of the resulting framework on the problem of redundant end-effector tracking for both a simulated 3 degrees of freedom robot arm as well as for a simulated anthropomorphic SARCOS Master Arm. While learning to execute tasks in task space is an essential component to a general framework to motor skill learning, learning the actual task is of even higher importance, particularly as this issue is more frequently beyond the abilities of analytical approaches than execution. We focus on the learning of elemental tasks which can serve as the "building blocks of movement generation", called motor primitives. Motor primitives are parameterized task representations based on splines or nonlinear differential equations with desired attractor properties. While imitation learning of parameterized motor primitives is a relatively well-understood problem, the self-improvement by interaction of the system with the environment remains a challenging problem, tackled in the fourth chapter of this thesis. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and outline both established and novel algorithms for the gradient-based improvement of parameterized policies. We compare these algorithms in the context of motor primitive learning, and show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. In conclusion, in this thesis, we have contributed a general framework for analytically computing robot control laws which can be used for deriving various previous control approaches and serves as foundation as well as inspiration for our learning algorithms. We have introduced two classes of novel reinforcement learning methods, i.e., the Natural Actor-Critic and the Reward-Weighted Regression algorithm. These algorithms have been used in order to replace the analytical components of the theoretical framework by learned representations. Evaluations have been performed on both simulated and real robot arms.

[BibTex]

[BibTex]


no image
Reinforcement learning by reward-weighted regression for operational space control

Peters, J., Schaal, S.

In Proceedings of the 24th Annual International Conference on Machine Learning, pages: 745-750, ICML, 2007, clmc (inproceedings)

Abstract
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-base reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Policy gradient methods for machine learning

Peters, J., Theodorou, E., Schaal, S.

In Proceedings of the 14th INFORMS Conference of the Applied Probability Society, pages: 97-98, Eindhoven, Netherlands, July 9-11, 2007, 2007, clmc (inproceedings)

Abstract
We present an in-depth survey of policy gradient methods as they are used in the machine learning community for optimizing parameterized, stochastic control policies in Markovian systems with respect to the expected reward. Despite having been developed separately in the reinforcement learning literature, policy gradient methods employ likelihood ratio gradient estimators as also suggested in the stochastic simulation optimization community. It is well-known that this approach to policy gradient estimation traditionally suffers from three drawbacks, i.e., large variance, a strong dependence on baseline functions and a inefficient gradient descent. In this talk, we will present a series of recent results which tackles each of these problems. The variance of the gradient estimation can be reduced significantly through recently introduced techniques such as optimal baselines, compatible function approximations and all-action gradients. However, as even the analytically obtainable policy gradients perform unnaturally slow, it required the step from ÔvanillaÕ policy gradient methods towards natural policy gradients in order to overcome the inefficiency of the gradient descent. This development resulted into the Natural Actor-Critic architecture which can be shown to be very efficient in application to motor primitive learning for robotics.

[BibTex]

[BibTex]


no image
Policy Learning for Motor Skills

Peters, J., Schaal, S.

In Proceedings of 14th International Conference on Neural Information Processing (ICONIP), pages: 233-242, (Editors: Ishikawa, M. , K. Doya, H. Miyamoto, T. Yamakawa), 2007, clmc (inproceedings)

Abstract
Policy learning which allows autonomous robots to adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach policy learning with the goal of an application to motor skill refinement in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, we study policy learning algorithms which can be applied in the general setting of motor skill learning, and, secondly, we study a theoretically well-founded general approach to representing the required control structures for task representation and execution.

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Reinforcement learning for operational space control

Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Conference on Robotics and Automation, pages: 2111-2116, IEEE Computer Society, ICRA, 2007, clmc (inproceedings)

Abstract
While operational space control is of essential importance for robotics and well-understood from an analytical point of view, it can be prohibitively hard to achieve accurate control in face of modeling errors, which are inevitable in complex robots, e.g., humanoid robots. In such cases, learning control methods can offer an interesting alternative to analytical control algorithms. However, the resulting supervised learning problem is ill-defined as it requires to learn an inverse mapping of a usually redundant system, which is well known to suffer from the property of non-convexity of the solution space, i.e., the learning system could generate motor commands that try to steer the robot into physically impossible configurations. The important insight that many operational space control algorithms can be reformulated as optimal control problems, however, allows addressing this inverse learning problem in the framework of reinforcement learning. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-based reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Relative Entropy Policy Search

Peters, J.

CLMC Technical Report: TR-CLMC-2007-2, Computational Learning and Motor Control Lab, Los Angeles, CA, 2007, clmc (techreport)

Abstract
This technical report describes a cute idea of how to create new policy search approaches. It directly relates to the Natural Actor-Critic methods but allows the derivation of one shot solutions. Future work may include the application to interesting problems.

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Using reward-weighted regression for reinforcement learning of task space control

Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pages: 262-267, Honolulu, Hawaii, April 1-5, 2007, 2007, clmc (inproceedings)

Abstract
In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, `vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark

Riedmiller, M., Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pages: 254-261, ADPRL, 2007, clmc (inproceedings)

Abstract
In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, `vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

PDF [BibTex]

PDF [BibTex]

2002


no image
Real-Time Statistical Learning for Oculomotor Control and Visuomotor Coordination

Vijayakumar, S., Souza, A., Peters, J., Conradt, J., Rutkowski, T., Ijspeert, A., Nakanishi, J., Inoue, M., Shibata, T., Wiryo, A., Itti, L., Amari, S., Schaal, S.

(Editors: Becker, S. , S. Thrun, K. Obermayer), Sixteenth Annual Conference on Neural Information Processing Systems (NIPS), December 2002 (poster)

Web [BibTex]

2002

Web [BibTex]


no image
Optimized Support Vector Machines for Nonstationary Signal Classification

Davy, M., Gretton, A., Doucet, A., Rayner, P.

IEEE Signal Processing Letters, 9(12):442-445, December 2002 (article)

Abstract
This letter describes an efficient method to perform nonstationary signal classification. A support vector machine (SVM) algorithm is introduced and its parameters optimised in a principled way. Simulations demonstrate that our low complexity method outperforms state-of-the-art nonstationary signal classification techniques.

PostScript Web DOI [BibTex]

PostScript Web DOI [BibTex]


no image
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond

Schölkopf, B., Smola, A.

pages: 644, Adaptive Computation and Machine Learning, MIT Press, Cambridge, MA, USA, December 2002, Parts of this book, including an introduction to kernel methods, can be downloaded here. (book)

Abstract
In the 1990s, a new type of learning algorithm was developed, based on results from statistical learning theory: the Support Vector Machine (SVM). This gave rise to a new class of theoretically elegant learning machines that use a central concept of SVMs-kernels—for a number of learning tasks. Kernel machines provide a modular framework that can be adapted to different tasks and domains by the choice of the kernel function and the base algorithm. They are replacing neural networks in a variety of fields, including engineering, information retrieval, and bioinformatics. Learning with Kernels provides an introduction to SVMs and related kernel methods. Although the book begins with the basics, it also includes the latest research. It provides all of the concepts necessary to enable a reader equipped with some basic mathematical knowledge to enter the world of machine learning using theoretically well-founded yet easy-to-use kernel algorithms and to understand and apply the powerful algorithms that have been developed over the last few years.

Web [BibTex]

Web [BibTex]


no image
Surface-slant-from-texture discrimination: Effects of slant level and texture type

Rosas, P., Wichmann, F., Wagemans, J.

Journal of Vision, 2(7):300, Second Annual Meeting of the Vision Sciences Society (VSS), November 2002 (poster)

Abstract
The problem of surface-slant-from-texture was studied psychophysically by measuring the performances of five human subjects in a slant-discrimination task with a number of different types of textures: uniform lattices, randomly displaced lattices, polka dots, Voronoi tessellations, orthogonal sinusoidal plaid patterns, fractal or 1/f noise, “coherent” noise and a “diffusion-based” texture (leopard skin-like). The results show: (1) Improving performance with larger slants for all textures. (2) A “non-symmetrical” performance around a particular slant characterized by a psychometric function that is steeper in the direction of the more slanted orientation. (3) For sufficiently large slants (66 deg) there are no major differences in performance between any of the different textures. (4) For slants at 26, 37 and 53 degrees, however, there are marked differences between the different textures. (5) The observed differences in performance across textures for slants up to 53 degrees are systematic within subjects, and nearly so across them. This allows a rank-order of textures to be formed according to their “helpfulness” — that is, how easy the discrimination task is when a particular texture is mapped on the surface. Polka dots tended to allow the best slant discrimination performance, noise patterns the worst up to the large slant of 66 degrees at which performance was almost independent of the particular texture chosen. Finally, our large number of 2AFC trials (approximately 2800 trials per texture across subjects) and associated tight confidence intervals may enable us to find out about which statistical properties of the textures could be responsible for surface-slant-from-texture estimation, with the ultimate goal of being able to predict observer performance for any arbitrary texture.

Web DOI [BibTex]

Web DOI [BibTex]


no image
Modelling Contrast Transfer in Spatial Vision

Wichmann, F.

Journal of Vision, 2(10):7, Second Annual Meeting of the Vision Sciences Society (VSS), November 2002 (poster)

Abstract
Much of our information about spatial vision comes from detection experiments involving low-contrast stimuli. Contrast discrimination experiments provide one way to explore the visual system's response to stimuli of higher contrast, the results of which allow different models of contrast processing (e.g. energy versus gain-control models) to be critically assessed (Wichmann & Henning, 1999). Studies of detection and discrimination using pulse train stimuli in noise, on the other hand, make predictions about the number, position and properties of noise sources within the processing stream (Henning, Bird & Wichmann, 2002). Here I report modelling results combining data from both sinusoidal and pulse train experiments in and without noise to arrive at a more tightly constrained model of early spatial vision.

Web DOI [BibTex]

Web DOI [BibTex]