Header logo is



no image
Causal Inference for Empirical Time Series Based on the Postulate of Independence of Cause and Mechanism

Besserve, M.

53rd Annual Allerton Conference on Communication, Control, and Computing, September 2015 (talk)

ei

[BibTex]

[BibTex]


Thumb xl toc image patent
Methods of forming dry adhesive structures

Sitti, M., Murphy, M., Aksak, B.

September 2015, US Patent 9,120,953 (patent)

Abstract
Methods of forming dry adhesives including a method of making a dry adhesive including applying a liquid polymer to the second end of the stem, molding the liquid polymer on the stem in a mold, wherein the mold includes a recess having a cross-sectional area that is less than a cross-sectional area of the second end of the stem, curing the liquid polymer in the mold to form a tip at the second end of the stem, wherein the tip includes a second layer stem; corresponding to the recess in the mold, and removing the tip from the mold after the liquid polymer cures.

pi

[BibTex]

[BibTex]


Thumb xl toc image patent
Micro-fiber arrays with tip coating and transfer method for preparing same

Sitti, M., Washburn, N. R., Glass, P. S., Chung, H.

July 2015, US Patent 9,079,215 (patent)

Abstract
Present invention describes a patterned and coated micro- and nano-scale fibers elastomeric material for enhanced adhesion in wet or dry environments. A multi-step fabrication process including optical lithography, micromolding, polymer synthesis, dipping, stamping, and photopolymerization is described to produce uniform arrays of micron-scale fibers with mushroom-shaped tips coated with a thin layer of an intrinsically adhesive synthetic polymer, such as lightly crosslinked p(DMA-co-MEA).

pi

[BibTex]

[BibTex]


no image
Independence of cause and mechanism in brain networks

Besserve, M.

DALI workshop on Networks: Processes and Causality, April 2015 (talk)

ei

[BibTex]

[BibTex]


Thumb xl toc image patent
Dry adhesives and methods for making dry adhesives

Sitti, M., Murphy, M., Aksak, B.

March 2015, US Patent App. 14/625,162 (patent)

Abstract
Dry adhesives and methods for forming dry adhesives. A method of forming a dry adhesive structure on a substrate, comprises: forming a template backing layer of energy sensitive material on the substrate; forming a template layer of energy sensitive material on the template backing layer; exposing the template layer to a predetermined pattern of energy; removing a portion of the template layer related to the predetermined pattern of energy, and leaving a template structure formed from energy sensitive material and connected to the substrate via the template backing layer.

pi

[BibTex]

[BibTex]


no image
Information-Theoretic Implications of Classical and Quantum Causal Structures

Chaves, R., Majenz, C., Luft, L., Maciel, T., Janzing, D., Schölkopf, B., Gross, D.

18th Conference on Quantum Information Processing (QIP), 2015 (talk)

ei

Web link (url) [BibTex]

Web link (url) [BibTex]


no image
Assessment of brain tissue damage in the Sub-Acute Stroke Region by Multiparametric Imaging using [89-Zr]-Desferal-EPO-PET/MRI

Castaneda, S. G., Katiyar, P., Russo, F., Disselhorst, J. A., Calaminus, C., Poli, S., Maurer, A., Ziemann, U., Pichler, B. J.

World Molecular Imaging Conference, 2015 (talk)

ei

[BibTex]

[BibTex]


no image
Early time point in vivo PET/MR is a promising biomarker for determining efficacy of a novel Db(\alphaEGFR)-scTRAIL fusion protein therapy in a colon cancer model

Divine, M. R., Harant, M., Katiyar, P., Disselhorst, J. A., Bukala, D., Aidone, S., Siegemund, M., Pfizenmaier, K., Kontermann, R., Pichler, B. J.

World Molecular Imaging Conference, 2015 (talk)

ei

[BibTex]

[BibTex]


no image
The search for single exoplanet transits in the Kepler light curves

Foreman-Mackey, D., Hogg, D. W., Schölkopf, B.

IAU General Assembly, 22, pages: 2258352, 2015 (talk)

ei

link (url) [BibTex]

link (url) [BibTex]


Thumb xl thumb 9780262028370
Advanced Structured Prediction

Nowozin, S., Gehler, P. V., Jancsary, J., Lampert, C. H.

Advanced Structured Prediction, pages: 432, Neural Information Processing Series, MIT Press, November 2014 (book)

Abstract
The goal of structured prediction is to build machine learning models that predict relational information that itself has structure, such as being composed of multiple interrelated parts. These models, which reflect prior knowledge, task-specific relations, and constraints, are used in fields including computer vision, speech recognition, natural language processing, and computational biology. They can carry out such tasks as predicting a natural language sentence, or segmenting an image into meaningful components. These models are expressive and powerful, but exact computation is often intractable. A broad research effort in recent years has aimed at designing structured prediction models and approximate inference and learning procedures that are computationally efficient. This volume offers an overview of this recent research in order to make the work accessible to a broader research community. The chapters, by leading researchers in the field, cover a range of topics, including research trends, the linear programming relaxation approach, innovations in probabilistic modeling, recent theoretical progress, and resource-aware learning.

ps

publisher link (url) [BibTex]

publisher link (url) [BibTex]


Thumb xl toc image patent
Convertor

Fischer, P., Mark, A.

May 2014 (patent)

pf

[BibTex]

[BibTex]


no image
Method and device for blind correction of optical aberrations in a digital image

Schuler, C., Hirsch, M., Harmeling, S., Schölkopf, B.

International Patent Application, No. PCT/EP2012/068868, April 2014 (patent)

ei

[BibTex]


no image
Learning Motor Skills: From Algorithms to Robot Experiments

Kober, J., Peters, J.

97, pages: 191, Springer Tracts in Advanced Robotics, Springer, 2014 (book)

ei

DOI [BibTex]

DOI [BibTex]


no image
Computational Diffusion MRI and Brain Connectivity

Schultz, T., Nedjati-Gilani, G., Venkataraman, A., O’Donnell, L., Panagiotaki, E.

pages: 255, Mathematics and Visualization, Springer, 2014 (book)

ei

Web [BibTex]

Web [BibTex]


no image
Unsupervised identification of neural events in local field potentials

Besserve, M., Schölkopf, B., Logothetis, N. K.

44th Annual Meeting of the Society for Neuroscience (Neuroscience), 2014 (talk)

ei

[BibTex]

[BibTex]


no image
Quantifying statistical dependency

Besserve, M.

Research Network on Learning Systems Summer School, 2014 (talk)

ei

[BibTex]

[BibTex]


Thumb xl dissertation teaser scaled
Human Pose Estimation from Video and Inertial Sensors

Pons-Moll, G.

Ph.D Thesis, -, 2014 (book)

Abstract
The analysis and understanding of human movement is central to many applications such as sports science, medical diagnosis and movie production. The ability to automatically monitor human activity in security sensitive areas such as airports, lobbies or borders is of great practical importance. Furthermore, automatic pose estimation from images leverages the processing and understanding of massive digital libraries available on the Internet. We build upon a model based approach where the human shape is modelled with a surface mesh and the motion is parametrized by a kinematic chain. We then seek for the pose of the model that best explains the available observations coming from different sensors. In a first scenario, we consider a calibrated mult-iview setup in an indoor studio. To obtain very accurate results, we propose a novel tracker that combines information coming from video and a small set of Inertial Measurement Units (IMUs). We do so by locally optimizing a joint energy consisting of a term that measures the likelihood of the video data and a term for the IMU data. This is the first work to successfully combine video and IMUs information for full body pose estimation. When compared to commercial marker based systems the proposed solution is more cost efficient and less intrusive for the user. In a second scenario, we relax the assumption of an indoor studio and we tackle outdoor scenes with background clutter, illumination changes, large recording volumes and difficult motions of people interacting with objects. Again, we combine information from video and IMUs. Here we employ a particle based optimization approach that allows us to be more robust to tracking failures. To satisfy the orientation constraints imposed by the IMUs, we derive an analytic Inverse Kinematics (IK) procedure to sample from the manifold of valid poses. The generated hypothesis come from a lower dimensional manifold and therefore the computational cost can be reduced. Experiments on challenging sequences suggest the proposed tracker can be applied to capture in outdoor scenarios. Furthermore, the proposed IK sampling procedure can be used to integrate any kind of constraints derived from the environment. Finally, we consider the most challenging possible scenario: pose estimation of monocular images. Here, we argue that estimating the pose to the degree of accuracy as in an engineered environment is too ambitious with the current technology. Therefore, we propose to extract meaningful semantic information about the pose directly from image features in a discriminative fashion. In particular, we introduce posebits which are semantic pose descriptors about the geometric relationships between parts in the body. The experiments show that the intermediate step of inferring posebits from images can improve pose estimation from monocular imagery. Furthermore, posebits can be very useful as input feature for many computer vision algorithms.

ps

pdf [BibTex]

2006


no image
A Kernel Method for the Two-Sample-Problem

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

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

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

ei

PDF [BibTex]

2006


PDF [BibTex]


no image
Ab-initio gene finding using machine learning

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

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

ei

Web [BibTex]

Web [BibTex]


no image
Reinforcement Learning by Reward-Weighted Regression

Peters, J.

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

ei

Web [BibTex]

Web [BibTex]


no image
Graph boosting for molecular QSAR analysis

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

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

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

ei

Web [BibTex]

Web [BibTex]


no image
Inferring Causal Directions by Evaluating the Complexity of Conditional Distributions

Sun, X., Janzing, D., Schölkopf, B.

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

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

ei

Web [BibTex]


no image
Learning Optimal EEG Features Across Time, Frequency and Space

Farquhar, J., Hill, J., Schölkopf, B.

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

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Acquiring web page information without commitment to downloading the web page

Heilbron, L., Platt, J. C., Schölkopf, B., Simard, P. Y.

United States Patent, No 7155489, December 2006 (patent)

ei

[BibTex]

[BibTex]


no image
Semi-Supervised Learning

Zien, A.

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

ei

Web [BibTex]

Web [BibTex]


no image
A Machine Learning Approach for Determining the PET Attenuation Map from Magnetic Resonance Images

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

IEEE Medical Imaging Conference, November 2006 (talk)

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

ei

[BibTex]

[BibTex]


no image
Interactive images

Schölkopf, B., Toyama, K., Uyttendaele, M.

United States Patent, No 7120293, October 2006 (patent)

ei

[BibTex]

[BibTex]


no image
Semi-Supervised Support Vector Machines and Application to Spam Filtering

Zien, A.

ECML Discovery Challenge Workshop, September 2006 (talk)

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

ei

PDF Web [BibTex]


no image
Semi-Supervised Learning

Chapelle, O., Schölkopf, B., Zien, A.

pages: 508, Adaptive computation and machine learning, MIT Press, Cambridge, MA, USA, September 2006 (book)

Abstract
In the field of machine learning, semi-supervised learning (SSL) occupies the middle ground, between supervised learning (in which all training examples are labeled) and unsupervised learning (in which no label data are given). Interest in SSL has increased in recent years, particularly because of application domains in which unlabeled data are plentiful, such as images, text, and bioinformatics. This first comprehensive overview of SSL presents state-of-the-art algorithms, a taxonomy of the field, selected applications, benchmark experiments, and perspectives on ongoing and future research. Semi-Supervised Learning first presents the key assumptions and ideas underlying the field: smoothness, cluster or low-density separation, manifold structure, and transduction. The core of the book is the presentation of SSL methods, organized according to algorithmic strategies. After an examination of generative models, the book describes algorithms that implement the low-density separation assumption, graph-based methods, and algorithms that perform two-step learning. The book then discusses SSL applications and offers guidelines for SSL practitioners by analyzing the results of extensive benchmark experiments. Finally, the book looks at interesting directions for SSL research. The book closes with a discussion of the relationship between semi-supervised learning and transduction.

ei

Web [BibTex]

Web [BibTex]


no image
Inferential Structure Determination: Probabilistic determination and validation of NMR structures

Habeck, M.

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

ei

Web [BibTex]

Web [BibTex]


no image
Machine Learning Algorithms for Polymorphism Detection

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

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

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

ei

Web [BibTex]

Web [BibTex]


no image
Pattern detection methods and systems and face detection methods and systems

Blake, A., Romdhani, S., Schölkopf, B., Torr, P. H. S.

United States Patent, No 7099504, August 2006 (patent)

ei

[BibTex]

[BibTex]


no image
Inferential structure determination: Overview and new developments

Habeck, M.

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

ei

Web [BibTex]

Web [BibTex]


no image
MR/PET Attenuation Correction

Hofmann, M., Schölkopf, B., Steinke, F., Pichler, B.

Max-Planck-Gesellschaft, Biologische Kybernetik, July 2006 (patent)

ei

[BibTex]

[BibTex]


no image
MCMC inference in (Conditionally) Conjugate Dirichlet Process Gaussian Mixture Models

Rasmussen, C., Görür, D.

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

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

ei

Web [BibTex]

Web [BibTex]


no image
Sampling for non-conjugate infinite latent feature models

Görür, D., Rasmussen, C.

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

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

ei

PDF [BibTex]

PDF [BibTex]


no image
An Inventory of Sequence Polymorphisms For Arabidopsis

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

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

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

ei

[BibTex]

[BibTex]


no image
Machine Learning and Applications in Biology

Shin, H.

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

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

ei

PDF [BibTex]

PDF [BibTex]


no image
Gaussian Processes for Machine Learning

Rasmussen, CE., Williams, CKI.

pages: 248, Adaptive Computation and Machine Learning, MIT Press, Cambridge, MA, USA, January 2006 (book)

Abstract
Gaussian processes (GPs) provide a principled, practical, probabilistic approach to learning in kernel machines. GPs have received increased attention in the machine-learning community over the past decade, and this book provides a long-needed systematic and unified treatment of theoretical and practical aspects of GPs in machine learning. The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics. The book deals with the supervised-learning problem for both regression and classification, and includes detailed algorithms. A wide variety of covariance (kernel) functions are presented and their properties discussed. Model selection is discussed both from a Bayesian and a classical perspective. Many connections to other well-known techniques from machine learning and statistics are discussed, including support-vector machines, neural networks, splines, regularization networks, relevance vector machines and others. Theoretical issues including learning curves and the PAC-Bayesian framework are treated, and several approximation methods for learning with large datasets are discussed. The book contains illustrative examples and exercises, and code and datasets are available on the Web. Appendixes provide mathematical background and a discussion of Gaussian Markov processes.

ei

Web [BibTex]

Web [BibTex]


no image
Apparatus for Inspecting Alignment Film of Liquid Crystal Display and Method Thereof

Park, MW., Son, HI., Kim, SJ., Kim, KI., Yang, JW.

Max-Planck-Gesellschaft, Biologische Kybernetik, 2006 (patent)

ei

[BibTex]

[BibTex]


no image
Apparatus for Inspecting Flat Panel Display and Method Thereof

Yang, JW., Kim, KI., Son, HI.

Max-Planck-Gesellschaft, Biologische Kybernetik, 2006 (patent)

ei

[BibTex]

[BibTex]

2003


no image
Learning Control and Planning from the View of Control Theory and Imitation

Peters, J., Schaal, S.

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

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

ei

Web [BibTex]

2003


Web [BibTex]


no image
Recurrent neural networks from learning attractor dynamics

Schaal, S., Peters, J.

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

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

ei

Web [BibTex]

Web [BibTex]