Header logo is


2003


no image
Sparse Gaussian Processes: inference, subspace identification and model selection

Csato, L., Opper, M.

In Proceedings, pages: 1-6, (Editors: Van der Hof, , Wahlberg), The Netherlands, 13th IFAC Symposium on System Identifiaction, August 2003, electronical version; Index ThA02-2 (inproceedings)

Abstract
Gaussian Process (GP) inference is a probabilistic kernel method where the GP is treated as a latent function. The inference is carried out using the Bayesian online learning and its extension to the more general iterative approach which we call TAP/EP learning. Sparsity is introduced in this context to make the TAP/EP method applicable to large datasets. We address the prohibitive scaling of the number of parameters by defining a subset of the training data that is used as the support the GP, thus the number of required parameters is independent of the training set, similar to the case of ``Support--‘‘ or ``Relevance--Vectors‘‘. An advantage of the full probabilistic treatment is that allows the computation of the marginal data likelihood or evidence, leading to hyper-parameter estimation within the GP inference. An EM algorithm to choose the hyper-parameters is proposed. The TAP/EP learning is the E-step and the M-step then updates the hyper-parameters. Due to the sparse E-step the resulting algorithm does not involve manipulation of large matrices. The presented algorithm is applicable to a wide variety of likelihood functions. We present results of applying the algorithm on classification and nonstandard regression problems for artificial and real datasets.

ei

PDF GZIP [BibTex]

2003


PDF GZIP [BibTex]


no image
Adaptive, Cautious, Predictive control with Gaussian Process Priors

Murray-Smith, R., Sbarbaro, D., Rasmussen, CE., Girard, A.

In Proceedings of the 13th IFAC Symposium on System Identification, pages: 1195-1200, (Editors: Van den Hof, P., B. Wahlberg and S. Weiland), Proceedings of the 13th IFAC Symposium on System Identification, August 2003 (inproceedings)

Abstract
Nonparametric Gaussian Process models, a Bayesian statistics approach, are used to implement a nonlinear adaptive control law. Predictions, including propagation of the state uncertainty are made over a k-step horizon. The expected value of a quadratic cost function is minimised, over this prediction horizon, without ignoring the variance of the model predictions. The general method and its main features are illustrated on a simulation example.

ei

PDF [BibTex]

PDF [BibTex]


no image
Generative Model-based Clustering of Directional Data

Banerjee, A., Dhillon, I., Ghosh, J., Sra, S.

In Proc. ACK SIGKDD, pages: 00-00, KDD, August 2003 (inproceedings)

ei

GZIP [BibTex]

GZIP [BibTex]


no image
Hidden Markov Support Vector Machines

Altun, Y., Tsochantaridis, I., Hofmann, T.

In pages: 4-11, (Editors: Fawcett, T. , N. Mishra), AAAI Press, Menlo Park, CA, USA, Twentieth International Conference on Machine Learning (ICML), August 2003 (inproceedings)

ei

Web [BibTex]

Web [BibTex]


no image
How Many Neighbors To Consider in Pattern Pre-selection for Support Vector Classifiers?

Shin, H., Cho, S.

In Proc. of INNS-IEEE International Joint Conference on Neural Networks (IJCNN 2003), pages: 565-570, IJCNN, July 2003 (inproceedings)

Abstract
Training support vector classifiers (SVC) requires large memory and long cpu time when the pattern set is large. To alleviate the computational burden in SVC training, we previously proposed a preprocessing algorithm which selects only the patterns in the overlap region around the decision boundary, based on neighborhood properties [8], [9], [10]. The k-nearest neighbors’ class label entropy for each pattern was used to estimate the pattern’s proximity to the decision boundary. The value of parameter k is critical, yet has been determined by a rather ad-hoc fashion. We propose in this paper a systematic procedure to determine k and show its effectiveness through experiments.

ei

PDF [BibTex]

PDF [BibTex]


no image
On the Representation, Learning and Transfer of Spatio-Temporal Movement Characteristics

Ilg, W., Bakir, GH., Mezger, J., Giese, MA.

In Humanoids Proceedings, pages: 0-0, Humanoids Proceedings, July 2003, electronical version (inproceedings)

Abstract
In this paper we present a learning-based approach for the modelling of complex movement sequences. Based on the method of Spatio-Temporal Morphable Models (STMMS. We derive a hierarchical algorithm that, in a first step, identifies automatically movement elements in movement sequences based on a coarse spatio-temporal description, and in a second step models these movement primitives by approximation through linear combinations of learned example movement trajectories. We describe the different steps of the algorithm and show how it can be applied for modelling and synthesis of complex sequences of human movements that contain movement elements with variable style. The proposed method is demonstrated on different applications of movement representation relevant for imitation learning of movement styles in humanoid robotics.

ei

PDF [BibTex]

PDF [BibTex]


no image
Loss Functions and Optimization Methods for Discriminative Learning of Label Sequences

Altun, Y., Johnson, M., Hofmann, T.

In pages: 145-152, (Editors: Collins, M. , M. Steedman), ACL, East Stroudsburg, PA, USA, Conference on Empirical Methods in Natural Language Processing (EMNLP) , July 2003 (inproceedings)

Abstract
Discriminative models have been of interest in the NLP community in recent years. Previous research has shown that they are advantageous over generative models. In this paper, we investigate how different objective functions and optimization methods affect the performance of the classifiers in the discriminative learning framework. We focus on the sequence labelling problem, particularly POS tagging and NER tasks. Our experiments show that changing the objective function is not as effective as changing the features included in the model.

ei

Web [BibTex]

Web [BibTex]


no image
Time Complexity Analysis of Fast Pattern Selection Algorithm for SVM

Shin, H., Cho, S.

In Proc. of the Korean Data Mining Conference, pages: 221-231, Korean Data Mining Conference, June 2003 (inproceedings)

ei

[BibTex]

[BibTex]


no image
Fast Pattern Selection for Support Vector Classifiers

Shin, H., Cho, S.

In PAKDD 2003, pages: 376-387, (Editors: Whang, K.-Y. , J. Jeon, K. Shim, J. Srivastava), Springer, Berlin, Germany, 7th Pacific-Asia Conference on Knowledge Discovery and Data Mining, May 2003 (inproceedings)

Abstract
Training SVM requires large memory and long cpu time when the pattern set is large. To alleviate the computational burden in SVM training, we propose a fast preprocessing algorithm which selects only the patterns near the decision boundary. Preliminary simulation results were promising: Up to two orders of magnitude, training time reduction was achieved including the preprocessing, without any loss in classification accuracies.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Scaling Reinforcement Learning Paradigms for Motor Control

Peters, J., Vijayakumar, S., Schaal, S.

In JSNC 2003, 10, pages: 1-7, 10th Joint Symposium on Neural Computation (JSNC), May 2003 (inproceedings)

Abstract
Reinforcement learning offers a general framework to explain reward related learning in artificial and biological motor control. However, current reinforcement learning methods rarely scale to high dimensional movement systems and mainly operate in discrete, low dimensional domains like game-playing, artificial toy problems, etc. This drawback makes them unsuitable for application to human or bio-mimetic motor control. In this poster, we look at promising approaches that can potentially scale and suggest a novel formulation of the actor-critic algorithm which takes steps towards alleviating the current shortcomings. We argue that methods based on greedy policies are not likely to scale into high-dimensional domains as they are problematic when used with function approximation – a must when dealing with continuous domains. We adopt the path of direct policy gradient based policy improvements since they avoid the problems of unstabilizing dynamics encountered in traditional value iteration based updates. While regular policy gradient methods have demonstrated promising results in the domain of humanoid notor control, we demonstrate that these methods can be significantly improved using the natural policy gradient instead of the regular policy gradient. Based on this, it is proved that Kakade’s ‘average natural policy gradient’ is indeed the true natural gradient. A general algorithm for estimating the natural gradient, the Natural Actor-Critic algorithm, is introduced. This algorithm converges with probability one to the nearest local minimum in Riemannian space of the cost function. The algorithm outperforms nonnatural policy gradients by far in a cart-pole balancing evaluation, and offers a promising route for the development of reinforcement learning for truly high-dimensionally continuous state-action systems. Keywords: Reinforcement learning, neurodynamic programming, actorcritic methods, policy gradient methods, natural policy gradient

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
A case based comparison of identification with neural network and Gaussian process models.

Kocijan, J., Banko, B., Likar, B., Girard, A., Murray-Smith, R., Rasmussen, CE.

In Proceedings of the International Conference on Intelligent Control Systems and Signal Processing ICONS 2003, 1, pages: 137-142, (Editors: Ruano, E.A.), Proceedings of the International Conference on Intelligent Control Systems and Signal Processing ICONS, April 2003 (inproceedings)

Abstract
In this paper an alternative approach to black-box identification of non-linear dynamic systems is compared with the more established approach of using artificial neural networks. The Gaussian process prior approach is a representative of non-parametric modelling approaches. It was compared on a pH process modelling case study. The purpose of modelling was to use the model for control design. The comparison revealed that even though Gaussian process models can be effectively used for modelling dynamic systems caution has to be axercised when signals are selected.

ei

PDF [BibTex]

PDF [BibTex]


no image
On-Line One-Class Support Vector Machines. An Application to Signal Segmentation

Gretton, A., Desobry, ..

In IEEE ICASSP Vol. 2, pages: 709-712, IEEE ICASSP, April 2003 (inproceedings)

Abstract
In this paper, we describe an efficient algorithm to sequentially update a density support estimate obtained using one-class support vector machines. The solution provided is an exact solution, which proves to be far more computationally attractive than a batch approach. This deterministic technique is applied to the problem of audio signal segmentation, with simulations demonstrating the computational performance gain on toy data sets, and the accuracy of the segmentation on audio signals.

ei

PostScript [BibTex]

PostScript [BibTex]


no image
Blind separation of post-nonlinear mixtures using gaussianizing transformations and temporal decorrelation

Ziehe, A., Kawanabe, M., Harmeling, S., Müller, K.

In ICA 2003, pages: 269-274, (Editors: Amari, S.-I. , A. Cichocki, S. Makino, N. Murata), 4th International Symposium on Independent Component Analysis and Blind Signal Separation, April 2003 (inproceedings)

Abstract
At the previous workshop (ICA2001) we proposed the ACE-TD method that reduces the post-nonlinear blind source separation problem (PNL BSS) to a linear BSS problem. The method utilizes the Alternating Conditional Expectation (ACE) algorithm to approximately invert the (post-){non-linear} functions. In this contribution, we propose an alternative procedure called Gaussianizing transformation, which is motivated by the fact that linearly mixed signals before nonlinear transformation are approximately Gaussian distributed. This heuristic, but simple and efficient procedure yields similar results as the ACE method and can thus be used as a fast and effective equalization method. After equalizing the nonlinearities, temporal decorrelation separation (TDSEP) allows us to recover the source signals. Numerical simulations on realistic examples are performed to compare "Gauss-TD" with "ACE-TD".

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
The Kernel Mutual Information

Gretton, A., Herbrich, R., Smola, A.

In IEEE ICASSP Vol. 4, pages: 880-883, IEEE ICASSP, April 2003 (inproceedings)

Abstract
We introduce a new contrast function, the kernel mutual information (KMI), to measure the degree of independence of continuous random variables. This contrast function provides an approximate upper bound on the mutual information, as measured near independence, and is based on a kernel density estimate of the mutual information between a discretised approximation of the continuous random variables. We show that Bach and Jordan‘s kernel generalised variance (KGV) is also an upper bound on the same kernel density estimate, but is looser. Finally, we suggest that the addition of a regularising term in the KGV causes it to approach the KMI, which motivates the introduction of this regularisation.

ei

PostScript [BibTex]

PostScript [BibTex]


no image
Analysing ICA component by injection noise

Harmeling, S., Meinecke, F., Müller, K.

In ICA 2003, pages: 149-154, (Editors: Amari, S.-I. , A. Cichocki, S. Makino, N. Murata), 4th International Symposium on Independent Component Analysis and Blind Signal Separation, April 2003 (inproceedings)

Abstract
Usually, noise is considered to be destructive. We present a new method that constructively injects noise to assess the reliability and the group structure of empirical ICA components. Simulations show that the true root-mean squared angle distances between the real sources and some source estimates can be approximated by our method. In a toy experiment, we see that we are also able to reveal the underlying group structure of extracted ICA components. Furthermore, an experiment with fetal ECG data demonstrates that our approach is useful for exploratory data analysis of real-world data.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
A Gaussian mixture model for the motor cortical coding of hand motion

Wu, W., Mumford, D., Black, M. J., Gao, Y., Bienenstock, E., Donoghue, J. P.

Neural Control of Movement, Santa Barbara, CA, April 2003 (conference)

ps

abstract [BibTex]

abstract [BibTex]


no image
Dynamic movement primitives - A framework for motor control in humans and humanoid robots

Schaal, S.

In The International Symposium on Adaptive Motion of Animals and Machines, Kyoto, Japan, March 4-8, 2003, March 2003, clmc (inproceedings)

Abstract
Sensory-motor integration is one of the key issues in robotics. In this paper, we propose an approach to rhythmic arm movement control that is synchronized with an external signal based on exploiting a simple neural oscillator network. Trajectory generation by the neural oscillator is a biologically inspired method that can allow us to generate a smooth and continuous trajectory. The parameter tuning of the oscillators is used to generate a synchronized movement with wide intervals. We adopted the method for the drumming task as an example task. By using this method, the robot can realize synchronized drumming with wide drumming intervals in real time. The paper also shows the experimental results of drumming by a humanoid robot.

am

link (url) [BibTex]

link (url) [BibTex]


Thumb xl bildschirmfoto 2013 01 15 um 09.35.12
Connecting brains with machines: The neural control of 2D cursor movement

Black, M. J., Bienenstock, E., Donoghue, J. P., Serruya, M., Wu, W., Gao, Y.

In 1st International IEEE/EMBS Conference on Neural Engineering, pages: 580-583, Capri, Italy, March 2003 (inproceedings)

ps

pdf [BibTex]

pdf [BibTex]


Thumb xl bildschirmfoto 2013 01 15 um 09.44.01
A quantitative comparison of linear and non-linear models of motor cortical activity for the encoding and decoding of arm motions

Gao, Y., Black, M. J., Bienenstock, E., Wu, W., Donoghue, J. P.

In 1st International IEEE/EMBS Conference on Neural Engineering, pages: 189-192, Capri, Italy, March 2003 (inproceedings)

ps

pdf [BibTex]

pdf [BibTex]


no image
Hierarchical Spatio-Temporal Morphable Models for Representation of complex movements for Imitation Learning

Ilg, W., Bakir, GH., Franz, MO., Giese, M.

In 11th International Conference on Advanced Robotics, (2):453-458, (Editors: Nunes, U., A. de Almeida, A. Bejczy, K. Kosuge and J.A.T. Machado), 11th International Conference on Advanced Robotics, January 2003 (inproceedings)

ei

PDF [BibTex]

PDF [BibTex]


no image
Hyperkernels

Ong, CS., Smola, AJ., Williamson, RC.

In pages: 495-502, 2003 (inproceedings)

ei

PDF [BibTex]

PDF [BibTex]


no image
Feature Selection for Support Vector Machines by Means of Genetic Algorithms

Fröhlich, H., Chapelle, O., Schölkopf, B.

In 15th IEEE International Conference on Tools with AI, pages: 142-148, 15th IEEE International Conference on Tools with AI, 2003 (inproceedings)

ei

[BibTex]

[BibTex]


no image
Propagation of Uncertainty in Bayesian Kernel Models - Application to Multiple-Step Ahead Forecasting

Quiñonero-Candela, J., Girard, A., Larsen, J., Rasmussen, CE.

In IEEE International Conference on Acoustics, Speech and Signal Processing, 2, pages: 701-704, IEEE International Conference on Acoustics, Speech and Signal Processing, 2003 (inproceedings)

Abstract
The object of Bayesian modelling is the predictive distribution, which in a forecasting scenario enables improved estimates of forecasted values and their uncertainties. In this paper we focus on reliably estimating the predictive mean and variance of forecasted values using Bayesian kernel based models such as the Gaussian Process and the Relevance Vector Machine. We derive novel analytic expressions for the predictive mean and variance for Gaussian kernel shapes under the assumption of a Gaussian input distribution in the static case, and of a recursive Gaussian predictive density in iterative forecasting. The capability of the method is demonstrated for forecasting of time-series and compared to approximate methods.

ei

PDF PostScript [BibTex]

PDF PostScript [BibTex]


no image
Unsupervised Clustering of Images using their Joint Segmentation

Seldin, Y., Starik, S., Werman, M.

In The 3rd International Workshop on Statistical and Computational Theories of Vision (SCTV 2003), pages: 1-24, 3rd International Workshop on Statistical and Computational Theories of Vision (SCTV), 2003 (inproceedings)

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Kernel Methods and Their Applications to Signal Processing

Bousquet, O., Perez-Cruz, F.

In Proceedings. (ICASSP ‘03), Special Session on Kernel Methods, pages: 860 , ICASSP, 2003 (inproceedings)

Abstract
Recently introduced in Machine Learning, the notion of kernels has drawn a lot of interest as it allows to obtain non-linear algorithms from linear ones in a simple and elegant manner. This, in conjunction with the introduction of new linear classification methods such as the Support Vector Machines has produced significant progress. The successes of such algorithms is now spreading as they are applied to more and more domains. Many Signal Processing problems, by their non-linear and high-dimensional nature may benefit from such techniques. We give an overview of kernel methods and their recent applications.

ei

PDF PostScript [BibTex]

PDF PostScript [BibTex]


no image
Predictive control with Gaussian process models

Kocijan, J., Murray-Smith, R., Rasmussen, CE., Likar, B.

In Proceedings of IEEE Region 8 Eurocon 2003: Computer as a Tool, pages: 352-356, (Editors: Zajc, B. and M. Tkal), Proceedings of IEEE Region 8 Eurocon: Computer as a Tool, 2003 (inproceedings)

Abstract
This paper describes model-based predictive control based on Gaussian processes.Gaussian process models provide a probabilistic non-parametric modelling approach for black-box identification of non-linear dynamic systems. It offers more insight in variance of obtained model response, as well as fewer parameters to determine than other models. The Gaussian processes can highlight areas of the input space where prediction quality is poor, due to the lack of data or its complexity, by indicating the higher variance around the predicted mean. This property is used in predictive control, where optimisation of control signal takes the variance information into account. The predictive control principle is demonstrated on a simulated example of nonlinear system.

ei

PDF PostScript [BibTex]

PDF PostScript [BibTex]


no image
Distance-based classification with Lipschitz functions

von Luxburg, U., Bousquet, O.

In Learning Theory and Kernel Machines, Proceedings of the 16th Annual Conference on Computational Learning Theory, pages: 314-328, (Editors: Schölkopf, B. and M.K. Warmuth), Learning Theory and Kernel Machines, Proceedings of the 16th Annual Conference on Computational Learning Theory, 2003 (inproceedings)

Abstract
The goal of this article is to develop a framework for large margin classification in metric spaces. We want to find a generalization of linear decision functions for metric spaces and define a corresponding notion of margin such that the decision function separates the training points with a large margin. It will turn out that using Lipschitz functions as decision functions, the inverse of the Lipschitz constant can be interpreted as the size of a margin. In order to construct a clean mathematical setup we isometrically embed the given metric space into a Banach space and the space of Lipschitz functions into its dual space. Our approach leads to a general large margin algorithm for classification in metric spaces. To analyze this algorithm, we first prove a representer theorem. It states that there exists a solution which can be expressed as linear combination of distances to sets of training points. Then we analyze the Rademacher complexity of some Lipschitz function classes. The generality of the Lipschitz approach can be seen from the fact that several well-known algorithms are special cases of the Lipschitz algorithm, among them the support vector machine, the linear programming machine, and the 1-nearest neighbor classifier.

ei

PDF PostScript [BibTex]

PDF PostScript [BibTex]


no image
Semi-Supervised Learning through Principal Directions Estimation

Chapelle, O., Schölkopf, B., Weston, J.

In ICML Workshop, The Continuum from Labeled to Unlabeled Data in Machine Learning & Data Mining, pages: 7, ICML Workshop: The Continuum from Labeled to Unlabeled Data in Machine Learning & Data Mining, 2003 (inproceedings)

Abstract
We describe methods for taking into account unlabeled data in the training of a kernel-based classifier, such as a Support Vector Machines (SVM). We propose two approaches utilizing unlabeled points in the vicinity of labeled ones. Both of the approaches effectively modify the metric of the pattern space, either by using non-spherical Gaussian density estimates which are determined using EM, or by modifying the kernel function using displacement vectors computed from pairs of unlabeled and labeled points. The latter is linked to techniques for training invariant SVMs. We present experimental results indicating that the proposed technique can lead to substantial improvements of classification accuracy.

ei

PostScript [BibTex]

PostScript [BibTex]


no image
Machine Learning with Hyperkernels

Ong, CS., Smola, AJ.

In pages: 568-575, 2003 (inproceedings)

ei

PDF [BibTex]

PDF [BibTex]


no image
Gaussian Processes to Speed up Hybrid Monte Carlo for Expensive Bayesian Integrals

Rasmussen, CE.

In Bayesian Statistics 7, pages: 651-659, (Editors: J. M. Bernardo, M. J. Bayarri, J. O. Berger, A. P. Dawid, D. Heckerman, A. F. M. Smith and M. West), Bayesian Statistics 7, 2003 (inproceedings)

Abstract
Hybrid Monte Carlo (HMC) is often the method of choice for computing Bayesian integrals that are not analytically tractable. However the success of this method may require a very large number of evaluations of the (un-normalized) posterior and its partial derivatives. In situations where the posterior is computationally costly to evaluate, this may lead to an unacceptable computational load for HMC. I propose to use a Gaussian Process model of the (log of the) posterior for most of the computations required by HMC. Within this scheme only occasional evaluation of the actual posterior is required to guarantee that the samples generated have exactly the desired distribution, even if the GP model is somewhat inaccurate. The method is demonstrated on a 10 dimensional problem, where 200 evaluations suffice for the generation of 100 roughly independent points from the posterior. Thus, the proposed scheme allows Bayesian treatment of models with posteriors that are computationally demanding, such as models involving computer simulation.

ei

PDF PostScript Web [BibTex]

PDF PostScript Web [BibTex]


no image
Dimension Reduction Based on Orthogonality — a Decorrelation Method in ICA

Zhang, K., Chan, L.

In Artificial Neural Networks and Neural Information Processing - ICANN/ICONIP 2003, pages: 132-139, (Editors: O Kaynak and E Alpaydin and E Oja and L Xu), Springer, Berlin, Germany, International Conference on Artificial Neural Networks and International Conference on Neural Information Processing, ICANN/ICONIP, 2003, Lecture Notes in Computer Science, Volume 2714 (inproceedings)

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Bayesian backfitting

D’Souza, A., Vijayakumar, S., Schaal, S.

In Proceedings of the 10th Joint Symposium on Neural Computation (JSNC 2003), Irvine, CA, May 2003, 2003, clmc (inproceedings)

Abstract
We present an algorithm aimed at addressing both computational and analytical intractability of Bayesian regression models which operate in very high-dimensional, usually underconstrained spaces. Several domains of research frequently provide such datasets, including chemometrics [2], and human movement analysis [1]. The literature in nonparametric statistics provides interesting solutions such as Backfitting [3] and Partial Least Squares [4], which are extremely robust and efficient, yet lack a probabilistic interpretation that could place them in the context of current research in statistical learning algorithms that emphasize the estimation of confidence, posterior distributions, and model complexity. In order to achieve numerical robustness and low computational cost, we first derive a novel Bayesian interpretation of Backfitting (BB) as a computationally efficient regression algorithm. BBÕs learning complexity scales linearly with the input dimensionality by decoupling inference among individual input dimensions. We embed BB in an efficient, locally variational model selection mechanism that automatically grows the number of backfitting experts in a mixture-of-experts regression model. We demonstrate the effectiveness of the algorithm in performing principled regularization of model complexity when fitting nonlinear manifolds while avoiding the numerical hazards associated with highly underconstrained problems. We also note that this algorithm appears applicable in various areas of neural computation, e.g., in abstract models of computational neuroscience, or implementations of statistical learning on artificial systems.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Reinforcement learning for humanoid robotics

Peters, J., Vijayakumar, S., Schaal, S.

In IEEE-RAS International Conference on Humanoid Robots (Humanoids2003), Karlsruhe, Germany, Sept.29-30, 2003, clmc (inproceedings)

Abstract
Reinforcement learning offers one of the most general framework to take traditional robotics towards true autonomy and versatility. However, applying reinforcement learning to high dimensional movement systems like humanoid robots remains an unsolved problem. In this paper, we discuss different approaches of reinforcement learning in terms of their applicability in humanoid robotics. Methods can be coarsely classified into three different categories, i.e., greedy methods, `vanilla' policy gradient methods, and natural gradient methods. We discuss that greedy methods are not likely to scale into the domain humanoid robotics as they are problematic when used with function approximation. `Vanilla' policy gradient methods on the other hand have been successfully applied on real-world robots including at least one humanoid robot. We demonstrate that these methods can be significantly improved using the natural policy gradient instead of the regular policy gradient. A derivation of the natural policy gradient is provided, proving that the average policy gradient of Kakade (2002) is indeed the true natural gradient. A general algorithm for estimating the natural gradient, the Natural Actor-Critic algorithm, is introduced. This algorithm converges to the nearest local minimum of the cost function with respect to the Fisher information metric under suitable conditions. The algorithm outperforms non-natural policy gradients by far in a cart-pole balancing evaluation, and for learning nonlinear dynamic motor primitives for humanoid robot control. It offers a promising route for the development of reinforcement learning for truly high dimensionally continuous state-action systems.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Accuracy of manual spike sorting: Results for the Utah intracortical array

Wood, F., Fellows, M., Vargas-Irwin, C., Black, M. J., Donoghue, J. P.

Program No. 279.2. 2003, Abstract Viewer and Itinerary Planner, Society for Neuroscience, Washington, DC, 2003, Online (conference)

ps

abstract [BibTex]

abstract [BibTex]


no image
Specular flow and the perception of surface reflectance

Roth, S., Domini, F., Black, M. J.

Journal of Vision, 3 (9): 413a, 2003 (conference)

ps

abstract poster [BibTex]

abstract poster [BibTex]


no image
Grain boundary phase transitions in the Al-Mg system and their influence on high-strain rate superplasticity

Straumal, B. B., Lopez, G. A., Mittemeijer, E. J., Gust, W., Zhilyaev, A. P.

In 216-217, pages: 307-312, Moscow, Russia, 2003 (inproceedings)

mms

[BibTex]

[BibTex]


no image
High aspect ratio polymer micro/nano-structure manufacturing using nanoembossing, nanomolding and directed self-assembly

Sitti, M.

In ASME 2003 International Mechanical Engineering Congress and Exposition, pages: 293-297, 2003 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Nsf workshop on future directions in nano-scale systems, dynamics and control

Sitti, M.

In Automatic Control Conference (ACC), 2003 (inproceedings)

pi

[BibTex]

[BibTex]


no image
3-D nano-fiber manufacturing by controlled pulling of liquid polymers using nano-probes

Nain, A. S., Sitti, M.

In Nanotechnology, 2003. IEEE-NANO 2003. 2003 Third IEEE Conference on, 1, pages: 60-63, 2003 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Discovering imitation strategies through categorization of multi-cimensional data

Billard, A., Epars, Y., Schaal, S., Cheng, G.

In IEEE International Conference on Intelligent Robots and Systems (IROS 2003), Las Vegas, NV, Oct. 27-31, 2003, clmc (inproceedings)

Abstract
An essential problem of imitation is that of determining Ówhat to imitateÓ, i.e. to determine which of the many features of the demonstration are relevant to the task and which should be reproduced. The strategy followed by the imitator can be modeled as a hierarchical optimization system, which minimizes the discrepancy between two multidimensional datasets. We consider imitation of a manipulation task. To classify across manipulation strategies, we apply a probabilistic analysis to data in Cartesian and joint spaces. We determine a general metric that optimizes the policy of task reproduction, following strategy determination. The model successfully discovers strategies in six different manipulation tasks and controls task reproduction by a full body humanoid robot. or the complete path followed by the demonstrator. We follow a similar taxonomy and apply it to the learning and reproduction of a manipulation task by a humanoid robot. We take the perspective that the features of the movements to imitate are those that appear most frequently, i.e. the invariants in time. The model builds upon previous work [3], [4] and is composed of a hierarchical time delay neural network that extracts invariant features from a manipulation task performed by a human demonstrator. The system analyzes the Carthesian trajectories of the objects and the joint

am

link (url) [BibTex]

link (url) [BibTex]


no image
Scaling reinforcement learning paradigms for motor learning

Peters, J., Vijayakumar, S., Schaal, S.

In Proceedings of the 10th Joint Symposium on Neural Computation (JSNC 2003), Irvine, CA, May 2003, 2003, clmc (inproceedings)

Abstract
Reinforcement learning offers a general framework to explain reward related learning in artificial and biological motor control. However, current reinforcement learning methods rarely scale to high dimensional movement systems and mainly operate in discrete, low dimensional domains like game-playing, artificial toy problems, etc. This drawback makes them unsuitable for application to human or bio-mimetic motor control. In this poster, we look at promising approaches that can potentially scale and suggest a novel formulation of the actor-critic algorithm which takes steps towards alleviating the current shortcomings. We argue that methods based on greedy policies are not likely to scale into high-dimensional domains as they are problematic when used with function approximation Ð a must when dealing with continuous domains. We adopt the path of direct policy gradient based policy improvements since they avoid the problems of unstabilizing dynamics encountered in traditional value iteration based updates. While regular policy gradient methods have demonstrated promising results in the domain of humanoid notor control, we demonstrate that these methods can be significantly improved using the natural policy gradient instead of the regular policy gradient. Based on this, it is proved that KakadeÕs Ôaverage natural policy gradientÕ is indeed the true natural gradient. A general algorithm for estimating the natural gradient, the Natural Actor-Critic algorithm, is introduced. This algorithm converges with probability one to the nearest local minimum in Riemannian space of the cost function. The algorithm outperforms nonnatural policy gradients by far in a cart-pole balancing evaluation, and offers a promising route for the development of reinforcement learning for truly high-dimensionally continuous state-action systems.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Influence of grain boundary phase transitions on the diffusion-related properties

Straumal, B., Baretzky, B.

In Proceedings of the International Conference on Diffusion, Segregation and Stresses in Materials, pages: 53-64, Defect and Diffusion Forum, Scitec Publications Ltd., Moscow, Russia, 2003 (inproceedings)

mms

[BibTex]

[BibTex]


no image
Are carbon nanostructures an efficient hydrogen storage medium?

Hirscher, M., Becher, M., Haluska, M., von Zeppelin, F., Chen, X., Dettlaff-Weglikowska, U., Roth, S.

In 356-357, pages: 433-437, Annecy, France, 2003 (inproceedings)

mms

[BibTex]

[BibTex]


no image
Learning attractor landscapes for learning motor primitives

Ijspeert, A., Nakanishi, J., Schaal, S.

In Advances in Neural Information Processing Systems 15, pages: 1547-1554, (Editors: Becker, S.;Thrun, S.;Obermayer, K.), Cambridge, MA: MIT Press, 2003, clmc (inproceedings)

Abstract
If globally high dimensional data has locally only low dimensional distributions, it is advantageous to perform a local dimensionality reduction before further processing the data. In this paper we examine several techniques for local dimensionality reduction in the context of locally weighted linear regression. As possible candidates, we derive local versions of factor analysis regression, principle component regression, principle component regression on joint distributions, and partial least squares regression. After outlining the statistical bases of these methods, we perform Monte Carlo simulations to evaluate their robustness with respect to violations of their statistical assumptions. One surprising outcome is that locally weighted partial least squares regression offers the best average results, thus outperforming even factor analysis, the theoretically most appealing of our candidate techniques.Ê

am

link (url) [BibTex]

link (url) [BibTex]


no image
Manufacturing of two and three-dimensional micro/nanostructures by integrating optical tweezers with chemical assembly

Castelino, K., Satyanarayana, S., Sitti, M.

In Nanotechnology, 2003. IEEE-NANO 2003. 2003 Third IEEE Conference on, 1, pages: 56-59, 2003 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Grain boundary faceting phase transition and thermal grooving in Cu

Straumal, B. B., Polyakov, S. A., Bischoff, E., Mittemeijer, E. J., Gust, W.

In Proceedings of the International Conference on Diffusion, Segregation and Stresses in Materials, 216/217, pages: 93-100, Diffusion and Defect Data, Pt. A, Defect and Diffusion Forum, Scitec Publ., Moscow, 2003 (inproceedings)

mms

[BibTex]

[BibTex]


no image
Evolution of Fault-tolerant Self-replicating Structures

Righetti, L., Shokur, S., Capcarre, M.

In Advances in Artificial Life, pages: 278-288, Lecture Notes in Computer Science, Springer Berlin Heidelberg, 2003 (inproceedings)

Abstract
Designed and evolved self-replicating structures in cellular automata have been extensively studied in the past as models of Artificial Life. However, CAs, unlike their biological counterpart, are very brittle: any faulty cell usually leads to the complete destruction of any emerging structures, let alone self-replicating structures. A way to design fault-tolerant structures based on error-correcting-code has been presented recently [1], but it required a cumbersome work to be put into practice. In this paper, we get back to the original inspiration for these works, nature, and propose a way to evolve self-replicating structures, faults here being only an idiosyncracy of the environment.

mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Learning from demonstration and adaptation of biped locomotion with dynamical movement primitives

Nakanishi, J., Morimoto, J., Endo, G., Schaal, S., Kawato, M.

In Workshop on Robot Learning by Demonstration, IEEE International Conference on Intelligent Robots and Systems (IROS 2003), Las Vegas, NV, Oct. 27-31, 2003, clmc (inproceedings)

Abstract
In this paper, we report on our research for learning biped locomotion from human demonstration. Our ultimate goal is to establish a design principle of a controller in order to achieve natural human-like locomotion. We suggest dynamical movement primitives as a CPG of a biped robot, an approach we have previously proposed for learning and encoding complex human movements. Demonstrated trajectories are learned through the movement primitives by locally weighted regression, and the frequency of the learned trajectories is adjusted automatically by a novel frequency adaptation algorithm based on phase resetting and entrainment of oscillators. Numerical simulations demonstrate the effectiveness of the proposed locomotion controller.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Movement planning and imitation by shaping nonlinear attractors

Schaal, S.

In Proceedings of the 12th Yale Workshop on Adaptive and Learning Systems, Yale University, New Haven, CT, 2003, clmc (inproceedings)

Abstract
Given the continuous stream of movements that biological systems exhibit in their daily activities, an account for such versatility and creativity has to assume that movement sequences consist of segments, executed either in sequence or with partial or complete overlap. Therefore, a fundamental question that has pervaded research in motor control both in artificial and biological systems revolves around identifying movement primitives (a.k.a. units of actions, basis behaviors, motor schemas, etc.). What are the fundamental building blocks that are strung together, adapted to, and created for ever new behaviors? This paper summarizes results that led to the hypothesis of Dynamic Movement Primitives (DMP). DMPs are units of action that are formalized as stable nonlinear attractor systems. They are useful for autonomous robotics as they are highly flexible in creating complex rhythmic (e.g., locomotion) and discrete (e.g., a tennis swing) behaviors that can quickly be adapted to the inevitable perturbations of a dy-namically changing, stochastic environment. Moreover, DMPs provide a formal framework that also lends itself to investigations in computational neuroscience. A recent finding that allows creating DMPs with the help of well-understood statistical learning methods has elevated DMPs from a more heuristic to a principled modeling approach, and, moreover, created a new foundation for imitation learning. Theoretical insights, evaluations on a humanoid robot, and behavioral and brain imaging data will serve to outline the framework of DMPs for a general approach to motor control and imitation in robotics and biology.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Synthetic gecko foot-hair micro/nano-structures for future wall-climbing robots

Sitti, M., Fearing, R. S.

In Robotics and Automation, 2003. Proceedings. ICRA’03. IEEE International Conference on, 1, pages: 1164-1170, 2003 (inproceedings)

pi

[BibTex]

[BibTex]