Header logo is


2003


no image
Phase Information and the Recognition of Natural Images

Braun, D., Wichmann, F., Gegenfurtner, K.

6, pages: 138, (Editors: H.H. Bülthoff, K.R. Gegenfurtner, H.A. Mallot, R. Ulrich, F.A. Wichmann), 6. T{\"u}binger Wahrnehmungskonferenz (TWK), February 2003 (poster)

Abstract
Fourier phase plays an important role in determining image structure. For example, when the phase spectrum of an image showing a ower is swapped with the phase spectrum of an image showing a tank, then we will usually perceive a tank in the resulting image, even though the amplitude spectrum is still that of the ower. Also, when the phases of an image are randomly swapped across frequencies, the resulting image becomes impossible to recognize. Our goal was to evaluate the e ect of phase manipulations in a more quantitative manner. On each trial subjects viewed two images of natural scenes. The subject had to indicate which one of the two images contained an animal. The spectra of the images were manipulated by adding random phase noise at each frequency. The phase noise was uniformly distributed in the interval [;+], where  was varied between 0 degree and 180 degrees. Image pairs were displayed for 100 msec. Subjects were remarkably resistant to the addition of phase noise. Even with [120; 120] degree noise, subjects still were at a level of 75% correct. The introduction of phase noise leads to a reduction of image contrast. Subjects were slightly better than a simple prediction based on this contrast reduction. However, when contrast response functions were measured in the same experimental paradigm, we found that performance in the phase noise experiment was signi cantly lower than that predicted by the corresponding contrast reduction.

ei

Web [BibTex]

2003


Web [BibTex]


no image
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.

ei

Web [BibTex]

Web [BibTex]


no image
Constraints measures and reproduction of style in robot imitation learning

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

6, pages: 70, (Editors: H.H. Bülthoff, K.R. Gegenfurtner, H.A. Mallot, R. Ulrich, F.A. Wichmann), 6. T{\"u}binger Wahrnehmungskonferenz (TWK), February 2003 (poster)

Abstract
Imitation learning is frequently discussed as a method for generating complex behaviors in robots by imitating human actors. The kinematic and the dynamic properties of humans and robots are typically quite di erent, however. For this reason observed human trajectories cannot be directly transferred to robots, even if their geometry is humanoid. Instead the human trajectory must be approximated by trajectories that can be realized by the robot. During this approximation deviations from the human trajectory may arise that change the style of the executed movement. Alternatively, the style of the movement might be well reproduced, but the imitated trajectory might be suboptimal with respect to di erent constraint measures from robotics control, leading to non-robust behavior. Goal of the presented work is to quantify this trade-o between \imitation quality" and constraint compatibility for the imitation of complex writing movements. In our experiment, we used trajectory data from human writing movements (see the abstract of Ilg et al. in this volume). The human trajectories were mapped onto robot trajectories by minimizing an error measure that integrates constraints that are important for the imitation of movement style and a regularizing constraint that ensures smooth joint trajectories with low velocities. In a rst experiment, both the end-e ector position and the shoulder angle of the robot were optimized in order to achieve good imitation together with accurate control of the end-e ector position. In a second experiment only the end-e ector trajectory was imitated whereas the motion of the elbow joint was determined using the optimal inverse kinematic solution for the robot. For both conditions di erent constraint measures (dexterity and relative jointlimit distances) and a measure for imitation quality were assessed. By controling the weight of the regularization term we can vary continuously between robot behavior optimizing imitation quality, and behavior minimizing joint velocities.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Study of Human Classification using Psychophysics and Machine Learning

Graf, A., Wichmann, F., Bülthoff, H., Schölkopf, B.

6, pages: 149, (Editors: H.H. Bülthoff, K.R. Gegenfurtner, H.A. Mallot, R. Ulrich, F.A. Wichmann), 6. T{\"u}binger Wahrnehmungskonferenz (TWK), Febuary 2003 (poster)

Abstract
We attempt to reach a better understanding of classi cation in humans using both psychophysical and machine learning techniques. In our psychophysical paradigm the stimuli presented to the human subjects are modi ed using machine learning algorithms according to their responses. Frontal views of human faces taken from a processed version of the MPI face database are employed for a gender classi cation task. The processing assures that all heads have same mean intensity, same pixel-surface area and are centered. This processing stage is followed by a smoothing of the database in order to eliminate, as much as possible, scanning artifacts. Principal Component Analysis is used to obtain a low-dimensional representation of the faces in the database. A subject is asked to classify the faces and experimental parameters such as class (i.e. female/male), con dence ratings and reaction times are recorded. A mean classi cation error of 14.5% is measured and, on average, 0.5 males are classi ed as females and 21.3females as males. The mean reaction time for the correctly classi ed faces is 1229 +- 252 [ms] whereas the incorrectly classi ed faces have a mean reaction time of 1769 +- 304 [ms] showing that the reaction times increase with the subject's classi- cation error. Reaction times are also shown to decrease with increasing con dence, both for the correct and incorrect classi cations. Classi cation errors, reaction times and con dence ratings are then correlated to concepts of machine learning such as separating hyperplane obtained when considering Support Vector Machines, Relevance Vector Machines, boosted Prototype and K-means Learners. Elements near the separating hyperplane are found to be classi ed with more errors than those away from it. In addition, the subject's con dence increases when moving away from the hyperplane. A preliminary analysis on the available small number of subjects indicates that K-means classi cation seems to re ect the subject's classi cation behavior best. The above learnersare then used to generate \special" elements, or representations, of the low-dimensional database according to the labels given by the subject. A memory experiment follows where the representations are shown together with faces seen or unseen during the classi cation experiment. This experiment aims to assess the representations by investigating whether some representations, or special elements, are classi ed as \seen before" despite that they never appeared in the classi cation experiment, possibly hinting at their use during human classi cation.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
A Representation of Complex Movement Sequences Based on Hierarchical Spatio-Temporal Correspondence for Imitation Learning in Robotics

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

6, pages: 74, (Editors: H.H. Bülthoff, K.R. Gegenfurtner, H.A. Mallot, R. Ulrich, F.A. Wichmann), 6. T{\"u}binger Wahrnehmungskonferenz (TWK), February 2003 (poster)

Abstract
Imitation learning of complex movements has become a popular topic in neuroscience, as well as in robotics. A number of conceptual as well as practical problems are still unsolved. One example is the determination of the aspects of movements which are relevant for imitation. Problems concerning the movement representation are twofold: (1) The movement characteristics of observed movements have to be transferred from the perceptual level to the level of generated actions. (2) Continuous spaces of movements with variable styles have to be approximated based on a limited number of learned example sequences. Therefore, one has to use representation with a high generalisation capability. We present methods for the representation of complex movement sequences that addresses these questions in the context of the imitation learning of writing movements using a robot arm with human-like geometry. For the transfer of complex movements from perception to action we exploit a learning-based method that represents complex action sequences by linear combination of prototypical examples (Ilg and Giese, BMCV 2002). The method of hierarchical spatio-temporal morphable models (HSTMM) decomposes action sequences automatically into movement primitives. These primitives are modeled by linear combinations of a small number of learned example trajectories. The learned spatio-temporal models are suitable for the analysis and synthesis of long action sequences, which consist of movement primitives with varying style parameters. The proposed method is illustrated by imitation learning of complex writing movements. Human trajectories were recorded using a commercial motion capture system (VICON). In the rst step the recorded writing sequences are decomposed into movement primitives. These movement primitives can be analyzed and changed in style by de ning linear combinations of prototypes with di erent linear weight combinations. Our system can imitate writing movements of di erent actors, synthesize new writing styles and can even exaggerate the writing movements of individual actors. Words and writing movements of the robot look very natural, and closely match the natural styles. These preliminary results makes the proposed method promising for further applications in learning-based robotics. In this poster we focus on the acquisition of the movement representation (identi cation and segmentation of movement primitives, generation of new writing styles by spatio-temporal morphing). The transfer of the generated writing movements to the robot considering the given kinematic and dynamic constraints is discussed in Bakir et al (this volume).

ei

PDF Web [BibTex]

PDF Web [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
An Introduction to Variable and Feature Selection.

Guyon, I., Elisseeff, A.

Journal of Machine Learning, 3, pages: 1157-1182, 2003 (article)

ei

[BibTex]

[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
A Note on Parameter Tuning for On-Line Shifting Algorithms

Bousquet, O.

Max Planck Institute for Biological Cybernetics, Tübingen, Germany, 2003 (techreport)

Abstract
In this short note, building on ideas of M. Herbster [2] we propose a method for automatically tuning the parameter of the FIXED-SHARE algorithm proposed by Herbster and Warmuth [3] in the context of on-line learning with shifting experts. We show that this can be done with a memory requirement of $O(nT)$ and that the additional loss incurred by the tuning is the same as the loss incurred for estimating the parameter of a Bernoulli random variable.

ei

PDF PostScript [BibTex]

PDF PostScript [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
Extension of the nu-SVM range for classification

Perez-Cruz, F., Weston, J., Herrmann, D., Schölkopf, B.

In Advances in Learning Theory: Methods, Models and Applications, NATO Science Series III: Computer and Systems Sciences, Vol. 190, 190, pages: 179-196, NATO Science Series III: Computer and Systems Sciences, (Editors: J Suykens and G Horvath and S Basu and C Micchelli and J Vandewalle), IOS Press, Amsterdam, 2003 (inbook)

ei

[BibTex]

[BibTex]


no image
m-Alternative Forced Choice—Improving the Efficiency of the Method of Constant Stimuli

Jäkel, F.

Biologische Kybernetik, Graduate School for Neural and Behavioural Sciences, Tübingen, 2003 (diplomathesis)

ei

[BibTex]

[BibTex]


no image
New Approaches to Statistical Learning Theory

Bousquet, O.

Annals of the Institute of Statistical Mathematics, 55(2):371-389, 2003 (article)

Abstract
We present new tools from probability theory that can be applied to the analysis of learning algorithms. These tools allow to derive new bounds on the generalization performance of learning algorithms and to propose alternative measures of the complexity of the learning task, which in turn can be used to derive new learning algorithms.

ei

PostScript [BibTex]

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
An Introduction to Support Vector Machines

Schölkopf, B.

In Recent Advances and Trends in Nonparametric Statistics , pages: 3-17, (Editors: MG Akritas and DN Politis), Elsevier, Amsterdam, The Netherlands, 2003 (inbook)

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Statistical Learning and Kernel Methods in Bioinformatics

Schölkopf, B., Guyon, I., Weston, J.

In Artificial Intelligence and Heuristic Methods in Bioinformatics, 183, pages: 1-21, 3, (Editors: P Frasconi und R Shamir), IOS Press, Amsterdam, The Netherlands, 2003 (inbook)

ei

[BibTex]

[BibTex]


no image
Interactive Images

Toyama, K., Schölkopf, B.

(MSR-TR-2003-64), Microsoft Research, Cambridge, UK, 2003 (techreport)

Abstract
Interactive Images are a natural extension of three recent developments: digital photography, interactive web pages, and browsable video. An interactive image is a multi-dimensional image, displayed two dimensions at a time (like a standard digital image), but with which a user can interact to browse through the other dimensions. One might consider a standard video sequence viewed with a video player as a simple interactive image with time as the third dimension. Interactive images are a generalization of this idea, in which the third (and greater) dimensions may be focus, exposure, white balance, saturation, and other parameters. Interaction is handled via a variety of modes including those we call ordinal, pixel-indexed, cumulative, and comprehensive. Through exploration of three novel forms of interactive images based on color, exposure, and focus, we will demonstrate the compelling nature of interactive images.

ei

Web [BibTex]

Web [BibTex]


no image
A Short Introduction to Learning with Kernels

Schölkopf, B., Smola, A.

In Proceedings of the Machine Learning Summer School, Lecture Notes in Artificial Intelligence, Vol. 2600, pages: 41-64, LNAI 2600, (Editors: S Mendelson and AJ Smola), Springer, Berlin, Heidelberg, Germany, 2003 (inbook)

ei

[BibTex]

[BibTex]


no image
Bayesian Kernel Methods

Smola, A., Schölkopf, B.

In Advanced Lectures on Machine Learning, Machine Learning Summer School 2002, Lecture Notes in Computer Science, Vol. 2600, LNAI 2600, pages: 65-117, 0, (Editors: S Mendelson and AJ Smola), Springer, Berlin, Germany, 2003 (inbook)

ei

DOI [BibTex]

DOI [BibTex]


no image
Stability of ensembles of kernel machines

Elisseeff, A., Pontil, M.

In 190, pages: 111-124, NATO Science Series III: Computer and Systems Science, (Editors: Suykens, J., G. Horvath, S. Basu, C. Micchelli and J. Vandewalle), IOS press, Netherlands, 2003 (inbook)

ei

[BibTex]

[BibTex]


no image
Models of contrast transfer as a function of presentation time and spatial frequency.

Wichmann, F.

2003 (poster)

Abstract
Understanding contrast transduction is essential for understanding spatial vision. Using standard 2AFC contrast discrimination experiments conducted using a carefully calibrated display we previously showed that the shape of the threshold versus (pedestal) contrast (TvC) curve changes with presentation time and the performance level defined as threshold (Wichmann, 1999; Wichmann & Henning, 1999). Additional experiments looked at the change of the TvC curve with spatial frequency (Bird, Henning & Wichmann, 2002), and at how to constrain the parameters of models of contrast processing (Wichmann, 2002). Here I report modelling results both across spatial frequency and presentation time. An extensive model-selection exploration was performed using Bayesian confidence regions for the fitted parameters as well as cross-validation methods. Bird, C.M., G.B. Henning and F.A. Wichmann (2002). Contrast discrimination with sinusoidal gratings of different spatial frequency. Journal of the Optical Society of America A, 19, 1267-1273. Wichmann, F.A. (1999). Some aspects of modelling human spatial vision: contrast discrimination. Unpublished doctoral dissertation, The University of Oxford. Wichmann, F.A. & Henning, G.B. (1999). Implications of the Pedestal Effect for Models of Contrast-Processing and Gain-Control. OSA Annual Meeting Program, 62. Wichmann, F.A. (2002). Modelling Contrast Transfer in Spatial Vision [Abstract]. Journal of Vision, 2, 7a.

ei

[BibTex]


Thumb xl toc image
New electro-optic effect: Sum-frequency generation from optically active liquids in the presence of a dc electric field

Fischer, P., Buckingham, A., Beckwitt, K., Wiersma, D., Wise, F.

PHYSICAL REVIEW LETTERS, 91(17), 2003 (article)

Abstract
We report the observation of sum-frequency signals that depend linearly on an applied electrostatic field and that change sign with the handedness of an optically active solute. This recently predicted chiral electro-optic effect exists in the electric-dipole approximation. The static electric field gives rise to an electric-field-induced sum-frequency signal (an achiral third-order process) that interferes with the chirality-specific sum-frequency at second order. The cross-terms linear in the electrostatic field constitute the effect and may be used to determine the absolute sign of second- and third-order nonlinear-optical susceptibilities in isotropic media.

pf

DOI [BibTex]

DOI [BibTex]


Thumb xl toc image
Chiral and achiral contributions to sum-frequency generation from optically active solutions of binaphthol

Fischer, P., Wise, F., Albrecht, A.

JOURNAL OF PHYSICAL CHEMISTRY A, 107(40):8232-8238, 2003 (article)

Abstract
The nonlinear sum- and difference-frequency generation spectroscopies can be probes of molecular chirality in optically active systems. We present a tensorial analysis of the chirality-specific electric-dipolar sum-frequency-generation susceptibility and the achiral electric-quadrupolar and magnetic-dipolar nonlinearities at second order in isotropic media. The chiral and achiral contributions to the sum-frequency signal from the bulk of optically active solutions of 1,1'-bi-2-naphthol (2,2'-dehydroxy-1,1'-binaphthyl) can be distinguished, and the former dominates. Ab initio computations reveal the dramatic resonance enhancement that the isotropic component of the electric-dipolar three-wave mixing hyperpolarizability experiences. Away from resonance its magnitude rapidly decreases, as-unlike the vector component-it is zero in the static limit. The dispersion of the first hyperpolarizability is computed by a configuration interaction singles sum-over-states approach with explicit regard to the Franck-Condon active vibrational substructure for all resonant electronic states.

pf

DOI [BibTex]

DOI [BibTex]


no image
Synthetic gecko foot-hair micro/nano-structures as dry adhesives

Sitti, M., Fearing, R. S.

Journal of adhesion science and technology, 17(8):1055-1073, Taylor & Francis Group, 2003 (article)

pi

Project Page [BibTex]

Project Page [BibTex]


no image
Teleoperated touch feedback from the surfaces at the nanoscale: modeling and experiments

Sitti, M., Hashimoto, H.

IEEE/ASME transactions on mechatronics, 8(2):287-298, IEEE, 2003 (article)

pi

[BibTex]

[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
Mixing in Cu/Ge system by swift heavy ions

Kumar, S., Chauhan, R. S., Singh, R. P., Kabiraj, D., Sahoo, P. K., Rumbolz, C., Srivastava, S. K., Bolse, W., Avasthi, D. K.

{Nuclear Instruments \& Methods in Physics Research Section B-Beam Interactions with Materials and Atoms}, 212, pages: 242-245, 2003 (article)

mms

[BibTex]

[BibTex]


no image
Magnetic properties of [NdFeBx/Nbz]n multilayer films

Tsai, J. L., Chin, T. S., Yao, Y. D., Melsheimer, A., Fischer, S. F., Dragon, T., Kelsch, M., Kronmüller, H.

{Journal of Applied Physics}, 93(10):6915-6917, 2003 (article)

mms

[BibTex]

[BibTex]


no image
Analysis of the temperature dependence of the coercive field of Sm2Co17 based magnets

Kronmüller, H., Goll, D.

{Scripta Materialia}, 48(7):833-838, 2003 (article)

mms

[BibTex]

[BibTex]


no image
NMR studies of hydrogen motion in nanostructured hydrogen-graphite systems

Majer, G., Stanik, E., Orimo, S.

{Journal of Alloys and Compounds}, 356-357, pages: 617-621, 2003 (article)

mms

[BibTex]

[BibTex]


no image
Hydrogen diffusion in metallic and nanostructured materials

Majer, G., Eberle, U., Kimmerle, F., Stanik, E., Orimo, S.

{Physica B}, 328, pages: 81-89, 2003 (article)

mms

[BibTex]

[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
Electron density-of-states and the metal-insulator transition in LaHx

Barnes, R. G., Chang, C. T., Majer, G., Kaess, U.

{Journal of Alloys and Compounds}, 356-357, pages: 137-141, 2003 (article)

mms

[BibTex]

[BibTex]


no image
Magnetism and the Microstructure of Ferromagnetic Solids

Kronmüller, H., Fähnle, M.

pages: 432 p., 1st ed., Cambridge University Press, Cambridge, 2003 (book)

mms

[BibTex]

[BibTex]


no image
Electronic sputtering from HOPG: A study of angular dependence

Tripathi, A., Khan, S. A., Srivastava, S. K., Kumar, M., Kumar, S., Rao, S. V. S. N., Lakshmi, G. B. V. S., Siddiqui, A. M., Bajwa, N., Nagaraja, H. S., Mittal, V. K., Szökefalvi, A., Kurth, M., Pandey, A. C., Avasthi, D. K., Carstanjen, H. D.

{Nuclear Instruments and Methods B}, 212, pages: 402-406, 2003 (article)

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
Stress-induced relaxation mechanisms in single-crystalline titanomagnetites

Walz, F., Brabers, V. A. M., Brabers, J. H. V. J., Kronmüller, H.

{Journal of Physics-Condensed Matter}, 15(41):7029-7045, 2003 (article)

mms

[BibTex]

[BibTex]