178 results (BibTeX)

2009


Methods for feature selection in a learning machine

Weston, J., Elisseeff, A., Schölkopf, B., Pérez-Cruz, F.

United States Patent, No 7624074, November 2009 (patent)

[BibTex]

2009

[BibTex]


Acquiring web page information without commitment to downloading the web page

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

United States Patent, No 7565409, July 2009 (patent)

[BibTex]

[BibTex]


Pre−processed feature ranking for a support vector machine

Weston, J., Elisseeff, A., Schölkopf, B., Pérez-Cruz, F., Guyon, I.

United States Patent, No. 7475048, January 2009 (patent)

[BibTex]

[BibTex]


An introduction to Kernel Learning Algorithms

Gehler, P., Schölkopf, B.

In Kernel Methods for Remote Sensing Data Analysis, pages: 25-48, 2, (Editors: Gustavo Camps-Valls and Lorenzo Bruzzone), Wiley, New York, NY, USA, 2009 (inbook)

Abstract
Kernel learning algorithms are currently becoming a standard tool in the area of machine learning and pattern recognition. In this chapter we review the fundamental theory of kernel learning. As the basic building block we introduce the kernel function, which provides an elegant and general way to compare possibly very complex objects. We then review the concept of a reproducing kernel Hilbert space and state the representer theorem. Finally we give an overview of the most prominent algorithms, which are support vector classification and regression, Gaussian Processes and kernel principal analysis. With multiple kernel learning and structured output prediction we also introduce some more recent advancements in the field.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb md screen shot 2012 02 21 at 15.56.00  2
On feature combination for multiclass object classification

Gehler, P., Nowozin, S.

In Proceedings of the Twelfth IEEE International Conference on Computer Vision, pages: 221-228, ICCV, 2009, oral presentation (inproceedings)

project page, code, data GoogleScholar pdf DOI [BibTex]

project page, code, data GoogleScholar pdf DOI [BibTex]


Thermodynamic efficiency of information and heat flow

Allahverdyan, A., Janzing, D., Mahler, G.

Journal of Statistical Mechanics: Theory and Experiment, 2009(09):P09011, September 2009 (article)

Abstract
A basic task of information processing is information transfer (flow). P0 Here we study a pair of Brownian particles each coupled to a thermal bath at temperatures T1 and T2 . The information flow in such a system is defined via the time-shifted mutual information. The information flow nullifies at equilibrium, and its efficiency is defined as the ratio of the flow to the total entropy production in the system. For a stationary state the information flows from higher to lower temperatures, and its efficiency is bounded from above by (max[T1 , T2 ])/(|T1 − T2 |). This upper bound is imposed by the second law and it quantifies the thermodynamic cost for information flow in the present class of systems. It can be reached in the adiabatic situation, where the particles have widely different characteristic times. The efficiency of heat flow—defined as the heat flow over the total amount of dissipated heat—is limited from above by the same factor. There is a complementarity between heat and information flow: the set-up which is most efficient for the former is the least efficient for the latter and vice versa. The above bound for the efficiency can be (transiently) overcome in certain non-stationary situations, but the efficiency is still limited from above. We study yet another measure of information processing (transfer entropy) proposed in the literature. Though this measure does not require any thermodynamic cost, the information flow and transfer entropy are shown to be intimately related for stationary states.

PDF DOI [BibTex]

PDF DOI [BibTex]


Nearest Neighbor Clustering: A Baseline Method for Consistent Clustering with Arbitrary Objective Functions

Bubeck, S., von Luxburg, U.

Journal of Machine Learning Research, 10, pages: 657-698, March 2009 (article)

Abstract
Clustering is often formulated as a discrete optimization problem. The objective is to find, among all partitions of the data set, the best one according to some quality measure. However, in the statistical setting where we assume that the finite data set has been sampled from some underlying space, the goal is not to find the best partition of the given sample, but to approximate the true partition of the underlying space. We argue that the discrete optimization approach usually does not achieve this goal, and instead can lead to inconsistency. We construct examples which provably have this behavior. As in the case of supervised learning, the cure is to restrict the size of the function classes under consideration. For appropriate “small” function classes we can prove very general consistency theorems for clustering optimization schemes. As one particular algorithm for clustering with a restricted function space we introduce “nearest neighbor clustering”. Similar to the k-nearest neighbor classifier in supervised learning, this algorithm can be seen as a general baseline algorithm to minimize arbitrary clustering objective functions. We prove that it is statistically consistent for all commonly used clustering objective functions.

PDF Web [BibTex]


Prototype Classification: Insights from Machine Learning

Graf, A., Bousquet, O., Rätsch, G., Schölkopf, B.

Neural Computation, 21(1):272-300, January 2009 (article)

Abstract
We shed light on the discrimination between patterns belonging to two different classes by casting this decoding problem into a generalized prototype framework. The discrimination process is then separated into two stages: a projection stage that reduces the dimensionality of the data by projecting it on a line and a threshold stage where the distributions of the projected patterns of both classes are separated. For this, we extend the popular mean-of-class prototype classification using algorithms from machine learning that satisfy a set of invariance properties. We report a simple yet general approach to express different types of linear classification algorithms in an identical and easy-to-visualize formal framework using generalized prototypes where these prototypes are used to express the normal vector and offset of the hyperplane. We investigate nonmargin classifiers such as the classical prototype classifier, the Fisher classifier, and the relevance vector machine. We then study hard and soft margin cl assifiers such as the support vector machine and a boosted version of the prototype classifier. Subsequently, we relate mean-of-class prototype classification to other classification algorithms by showing that the prototype classifier is a limit of any soft margin classifier and that boosting a prototype classifier yields the support vector machine. While giving novel insights into classification per se by presenting a common and unified formalism, our generalized prototype framework also provides an efficient visualization and a principled comparison of machine learning classification.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


Does Cognitive Science Need Kernels?

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

Trends in Cognitive Sciences, 13(9):381-388, September 2009 (article)

Abstract
Kernel methods are among the most successful tools in machine learning and are used in challenging data analysis problems in many disciplines. Here we provide examples where kernel methods have proven to be powerful tools for analyzing behavioral data, especially for identifying features in categorization experiments. We also demonstrate that kernel methods relate to perceptrons and exemplar models of categorization. Hence, we argue that kernel methods have neural and psychological plausibility, and theoretical results concerning their behavior are therefore potentially relevant for human category learning. In particular, we believe kernel methods have the potential to provide explanations ranging from the implementational via the algorithmic to the computational level.

PDF Web DOI Project Page [BibTex]

PDF Web DOI Project Page [BibTex]


Efficient Subwindow Search: A Branch and Bound Framework for Object Localization

Lampert, C., Blaschko, M., Hofmann, T.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(12):2129-2142, December 2009 (article)

Abstract
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To estimate the object‘s location, one can take a sliding window approach, but this strongly increases the computational cost because the classifier or similarity function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages. It converges to a globally optimal solution typically in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive or sliding window search. We show how our method is applicable to different object detection and image retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest-neighbor classifiers based on the chi^2 distance. We demonstrate state-of-the-art localization performance of the resulting systems on the UIUC Cars data set, the PASCAL VOC 2006 data set, and in the PASCAL VOC 2007 competition.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


Generating Spike Trains with Specified Correlation Coefficients

Macke, J., Berens, P., Ecker, A., Tolias, A., Bethge, M.

Neural Computation, 21(2):397-423, February 2009 (article)

Abstract
Spike trains recorded from populations of neurons can exhibit substantial pairwise correlations between neurons and rich temporal structure. Thus, for the realistic simulation and analysis of neural systems, it is essential to have efficient methods for generating artificial spike trains with specified correlation structure. Here we show how correlated binary spike trains can be simulated by means of a latent multivariate gaussian model. Sampling from the model is computationally very efficient and, in particular, feasible even for large populations of neurons. The entropy of the model is close to the theoretical maximum for a wide range of parameters. In addition, this framework naturally extends to correlations over time and offers an elegant way to model correlated neural spike counts with arbitrary marginal distributions.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


Guest editorial: Special issue on robot learning, Part B

Peters, J., Ng, A.

Autonomous Robots, 27(2):91-92, August 2009 (article)

PDF PDF DOI [BibTex]

PDF PDF DOI [BibTex]


Implicit Wiener Series Analysis of Epileptic Seizure Recordings

Barbero, A., Franz, M., Drongelen, W., Dorronsoro, J., Schölkopf, B., Grosse-Wentrup, M.

In EMBC 2009, pages: 5304-5307, (Editors: Y Kim and B He and G Worrell and X Pan), IEEE Service Center, Piscataway, NJ, USA, 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, September 2009 (inproceedings)

Abstract
Implicit Wiener series are a powerful tool to build Volterra representations of time series with any degree of nonlinearity. A natural question is then whether higher order representations yield more useful models. In this work we shall study this question for ECoG data channel relationships in epileptic seizure recordings, considering whether quadratic representations yield more accurate classifiers than linear ones. To do so we first show how to derive statistical information on the Volterra coefficient distribution and how to construct seizure classification patterns over that information. As our results illustrate, a quadratic model seems to provide no advantages over a linear one. Nevertheless, we shall also show that the interpretability of the implicit Wiener series provides insights into the inter-channel relationships of the recordings.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


Varieties of Justification in Machine Learning

Corfield, D.

In Proceedings of Multiplicity and Unification in Statistics and Probability, pages: 1-10, Multiplicity and Unification in Statistics and Probability, June 2009 (inproceedings)

Abstract
The field of machine learning has flourished over the past couple of decades. With huge amounts of data available, efficient algorithms can learn to extrapolate from their training sets to become very accurate classifiers. For example, it is straightforward now to develop classifiers which achieve accuracies of around 99% on databases of handwritten digits. Now these algorithms have been devised by theorists who arrive at the problem of machine learning with a range of different philosophical outlooks on the subject of inductive reasoning. This has led to a wide range of theoretical rationales for their work. In this talk I shall classify the different forms of justification for inductive machine learning into four kinds, and make some comparisons between them. With little by way of theoretical knowledge to aid in the learning tasks, while the relevance of these justificatory approaches for the inductive reasoning of the natural sciences is questionable, certain issues surrounding the presuppositions of inductive reasoning are brought sharply into focus. In particular, Frequentist, Bayesian and MDL outlooks can be compared.

PDF Web [BibTex]

PDF Web [BibTex]


Denoising photographs using dark frames optimized by quadratic programming

Gomez Rodriguez, M., Kober, J., Schölkopf, B.

In Proceedings of the First IEEE International Conference on Computational Photography (ICCP 2009), pages: 1-9, IEEE, Piscataway, NJ, USA, First IEEE International Conference on Computational Photography (ICCP), April 2009 (inproceedings)

Abstract
Photographs taken with long exposure or high ISO setting may contain substantial amounts of noise, drastically reducing the Signal-To-Noise Ratio (SNR). This paper presents a novel optimization approach for denoising. It is based on a library of dark frames previously taken under varying conditions of temperature, ISO setting and exposure time, and a quality measure or prior for the class of images to denoise. The method automatically computes a synthetic dark frame that, when subtracted from an image, optimizes the quality measure. For specific choices of the quality measure, the denoising problem reduces to a quadratic programming (QP) problem that can be solved efficiently. We show experimentally that it is sufficient to consider a limited subsample of pixels when evaluating the quality measure in the optimization, in which case the complexity of the procedure does not depend on the size of the images but only on the number of dark frames. We provide quantitative experimental results showing that our method automatically computes dark frames that are competitive with those taken under idealized conditions (controlled temperature, ISO setting, exposure time, and averaging of multiple exposures). We provide application examples in astronomical image denoising. The method is validated on two CMOS SLRs.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


Effects of Stimulus Type and of Error-Correcting Code Design on BCI Speller Performance

Hill, J., Farquhar, J., Martens, S., Biessmann, F., Schölkopf, B.

In Advances in neural information processing systems 21, pages: 665-672, (Editors: D Koller and D Schuurmans and Y Bengio and L Bottou), Curran, Red Hook, NY, USA, 22nd Annual Conference on Neural Information Processing Systems (NIPS), June 2009 (inproceedings)

Abstract
From an information-theoretic perspective, a noisy transmission system such as a visual Brain-Computer Interface (BCI) speller could benefit from the use of errorcorrecting codes. However, optimizing the code solely according to the maximal minimum-Hamming-distance criterion tends to lead to an overall increase in target frequency of target stimuli, and hence a significantly reduced average target-to-target interval (TTI), leading to difficulties in classifying the individual event-related potentials (ERPs) due to overlap and refractory effects. Clearly any change to the stimulus setup must also respect the possible psychophysiological consequences. Here we report new EEG data from experiments in which we explore stimulus types and codebooks in a within-subject design, finding an interaction between the two factors. Our data demonstrate that the traditional, rowcolumn code has particular spatial properties that lead to better performance than one would expect from its TTIs and Hamming-distances alone, but nonetheless error-correcting codes can improve performance provided the right stimulus type is used.

PDF PDF Web [BibTex]

PDF PDF Web [BibTex]


Incorporating Prior Knowledge on Class Probabilities into Local Similarity Measures for Intermodality Image Registration

Hofmann, M., Schölkopf, B., Bezrukov, I., Cahill, N.

In Proceedings of the MICCAI 2009 Workshop on Probabilistic Models for Medical Image Analysis , pages: 220-231, (Editors: W Wells and S Joshi and K Pohl), PMMIA, September 2009 (inproceedings)

Abstract
We present a methodology for incorporating prior knowledge on class probabilities into the registration process. By using knowledge from the imaging modality, pre-segmentations, and/or probabilistic atlases, we construct vectors of class probabilities for each image voxel. By defining new image similarity measures for distribution-valued images, we show how the class probability images can be nonrigidly registered in a variational framework. An experiment on nonrigid registration of MR and CT full-body scans illustrates that the proposed technique outperforms standard mutual information (MI) and normalized mutual information (NMI) based registration techniques when measured in terms of target registration error (TRE) of manually labeled fiducials.

PDF Web [BibTex]

PDF Web [BibTex]


On Pairwise Kernels: An Efficient Alternative and Generalization Analysis

Kashima, H., Oyama, S., Yamanishi, Y., Tsuda, K.

In Advances in Knowledge Discovery and Data Mining: 13th Pacific-Asia Conference, pages: 1030-1037, (Editors: Theeramunkong, T. , B. Kijsirikul, N. Cercone, T. B. Ho), Springer, Berlin, Germany, PAKDD, April 2009 (inproceedings)

Abstract
Pairwise classification has many applications including network prediction, entity resolution, and collaborative filtering. The pairwise kernel has been proposed for those purposes by several research groups independently, and become successful in various fields. In this paper, we propose an efficient alternative which we call Cartesian kernel. While the existing pairwise kernel (which we refer to as Kronecker kernel) can be interpreted as the weighted adjacency matrix of the Kronecker product graph of two graphs, the Cartesian kernel can be interpreted as that of the Cartesian graph which is more sparse than the Kronecker product graph. Experimental results show the Cartesian kernel is much faster than the existing pairwise kernel, and at the same time, competitive with the existing pairwise kernel in predictive performance.We discuss the generalization bounds by the two pairwise kernels by using eigenvalue analysis of the kernel matrices.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


Convex Perturbations for Scalable Semidefinite Programming

Kulis, B., Sra, S., Dhillon, I.

In JMLR Workshop and Conference Proceedings Volume 5: AISTATS 2009, pages: 296-303, (Editors: van Dyk, D. , M. Welling), MIT Press, Cambridge, MA, USA, Twelfth International Conference on Artificial Intelligence and Statistics, April 2009 (inproceedings)

Abstract
Many important machine learning problems are modeled and solved via semidefinite programs; examples include metric learning, nonlinear embedding, and certain clustering problems. Often, off-the-shelf software is invoked for the associated optimization, which can be inappropriate due to excessive computational and storage requirements. In this paper, we introduce the use of convex perturbations for solving semidefinite programs (SDPs), and for a specific perturbation we derive an algorithm that has several advantages over existing techniques: a) it is simple, requiring only a few lines of Matlab, b) it is a first-order method, and thereby scalable, and c) it can easily exploit the structure of a given SDP (e.g., when the constraint matrices are low-rank, a situation common to several machine learning SDPs). A pleasant byproduct of our method is a fast, kernelized version of the large-margin nearest neighbor metric learning algorithm. We demonstrate that our algorithm is effective in finding fast approximations to large-scale SDPs arising in some machine learning applications.

PDF Web Project Page [BibTex]

PDF Web Project Page [BibTex]


Influence of graph construction on graph-based clustering measures

Maier, M., von Luxburg, U., Hein, M.

In Advances in neural information processing systems 21, pages: 1025-1032, (Editors: Koller, D. , D. Schuurmans, Y. Bengio, L. Bottou), Curran, Red Hook, NY, USA, Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS), June 2009 (inproceedings)

Abstract
Graph clustering methods such as spectral clustering are defined for general weighted graphs. In machine learning, however, data often is not given in form of a graph, but in terms of similarity (or distance) values between points. In this case, first a neighborhood graph is constructed using the similarities between the points and then a graph clustering algorithm is applied to this graph. In this paper we investigate the influence of the construction of the similarity graph on the clustering results. We first study the convergence of graph clustering criteria such as the normalized cut (Ncut) as the sample size tends to infinity. We find that the limit expressions are different for different types of graph, for example the r-neighborhood graph or the k-nearest neighbor graph. In plain words: Ncut on a kNN graph does something systematically different than Ncut on an r-neighborhood graph! This finding shows that graph clustering criteria cannot be studied independently of the kind of graph they are applied to. We also provide examples which show that these differences can be observed for toy and real data already for rather small sample sizes.

PDF Web [BibTex]

PDF Web [BibTex]


Local Gaussian Process Regression for Real Time Online Model Learning and Control

Nguyen-Tuong, D., Seeger, M., Peters, J.

In Advances in neural information processing systems 21, pages: 1193-1200, (Editors: Koller, D. , D. Schuurmans, Y. Bengio, L. Bottou), Curran, Red Hook, NY, USA, Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS), June 2009 (inproceedings)

Abstract
Learning in real-time applications, e.g., online approximation of the inverse dynamics model for model-based robot control, requires fast online regression techniques. Inspired by local learning, we propose a method to speed up standard Gaussian Process regression (GPR) with local GP models (LGP). The training data is partitioned in local regions, for each an individual GP model is trained. The prediction for a query point is performed by weighted estimation using nearby local models. Unlike other GP approximations, such as mixtures of experts, we use a distance based measure for partitioning of the data and weighted prediction. The proposed method achieves online learning and prediction in real-time. Comparisons with other nonparametric regression methods show that LGP has higher accuracy than LWPR and close to the performance of standard GPR and nu-SVR.

PDF Web [BibTex]

PDF Web [BibTex]


Detecting the Direction of Causal Time Series

Peters, J., Janzing, D., Gretton, A., Schölkopf, B.

In Proceedings of the 26th International Conference on Machine Learning, pages: 801-808, (Editors: A Danyluk and L Bottou and ML Littman), ACM Press, New York, NY, USA, ICML, June 2009 (inproceedings)

Abstract
We propose a method that detects the true direction of time series, by fitting an autoregressive moving average model to the data. Whenever the noise is independent of the previous samples for one ordering of the observations, but dependent for the opposite ordering, we infer the former direction to be the true one. We prove that our method works in the population case as long as the noise of the process is not normally distributed (for the latter case, the direction is not identificable). A new and important implication of our result is that it confirms a fundamental conjecture in causal reasoning - if after regression the noise is independent of signal for one direction and dependent for the other, then the former represents the true causal direction - in the case of time series. We test our approach on two types of data: simulated data sets conforming to our modeling assumptions, and real world EEG time series. Our method makes a decision for a significant fraction of both data sets, and these decisions are mostly correct. For real world data, our approach outperforms alternative solutions to the problem of time direction recovery.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


Inference algorithms and learning theory for Bayesian sparse factor analysis

Rattray, M. Stegle, O. Sharp, K. Winn, J.

Journal of Physics: Conference Series , IW-SMI 2009, 197(1: International Workshop on Statistical-Mechanical Informatics 2009):1-10, (Editors: Inoue, M. , S. Ishii, Y. Kabashima, M. Okada), Institute of Physics, Bristol, UK, International Workshop on Statistical-Mechanical Informatics (IW-SMI), September 2009 (article)

Abstract
Bayesian sparse factor analysis has many applications; for example, it has been applied to the problem of inferring a sparse regulatory network from gene expression data. We describe a number of inference algorithms for Bayesian sparse factor analysis using a slab and spike mixture prior. These include well-established Markov chain Monte Carlo (MCMC) and variational Bayes (VB) algorithms as well as a novel hybrid of VB and Expectation Propagation (EP). For the case of a single latent factor we derive a theory for learning performance using the replica method. We compare the MCMC and VB/EP algorithm results with simulated data to the theoretical prediction. The results for MCMC agree closely with the theory as expected. Results for VB/EP are slightly sub-optimal but show that the new algorithm is effective for sparse inference. In large-scale problems MCMC is infeasible due to computational limitations and the VB/EP algorithm then provides a very useful computationally efficient alternative.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


Block Jacobi-type methods for non-orthogonal joint diagonalisation

Shen, H., Hüper, K.

In ICASSP09, pages: 3285-3288, IEEE Service Center, Piscataway, NJ, USA, 34th International Conference on Acoustics, Speech, and Signal Processing, April 2009 (inproceedings)

Abstract
In this paper, we study the problem of non-orthogonal joint diagonalisation of a set of real symmetric matrices via simultaneous conjugation. A family of block Jacobi-type methods are proposed to optimise two popular cost functions for the non-orthogonal joint diagonalisation, namely, the off-norm function and the log-likelihood function. By exploiting the appropriate underlying manifold, namely the so-called oblique manifold, rigorous analysis shows that, under the exact non-orthogonal joint diagonalisation setting, the proposed methods converge locally quadratically fast to a joint diagonaliser. Finally, performance of our methods is investigated by numerical experiments for both exact and approximate non-orthogonal joint diagonalisation.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


Near-optimal supervised feature selection among frequent subgraphs

Thoma, M., Cheng, H., Gretton, A., Han, J., Kriegel, H., Smola, A., Song, L., Yu, P., Yan, X., Borgwardt, K.

In Proccedings of the 2009 SIAM Conference on Data Mining (SDM 2009), pages: 1076-1087, (Editors: Park, H. , S. Parthasarathy, H. Liu), Philadelphia, PA, USA, Society for Industrial and Applied Mathematics, 9th SIAM Conference on Data Mining (SDM), May 2009 (inproceedings)

Abstract
Graph classification is an increasingly important step in numerous application domains, such as function prediction of molecules and proteins, computerised scene analysis, and anomaly detection in program flows. Among the various approaches proposed in the literature, graph classification based on frequent subgraphs is a popular branch: Graphs are represented as (usually binary) vectors, with components indicating whether a graph contains a particular subgraph that is frequent across the dataset. On large graphs, however, one faces the enormous problem that the number of these frequent subgraphs may grow exponentially with the size of the graphs, but only few of them possess enough discriminative power to make them useful for graph classification. Efficient and discriminative feature selection among frequent subgraphs is hence a key challenge for graph mining. In this article, we propose an approach to feature selection on frequent subgraphs, called CORK, that combines two central advantages. First, it optimizes a submodular quality criterion, which means that we can yield a near-optimal solution using greedy feature selection. Second, our submodular quality function criterion can be integrated into gSpan, the state-of-the-art tool for frequent subgraph mining, and help to prune the search space for discriminative frequent subgraphs even during frequent subgraph mining.

PDF PDF [BibTex]

PDF PDF [BibTex]


Text Clustering with Mixture of von Mises-Fisher Distributions

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

In Text mining: classification, clustering, and applications, pages: 121-161, Chapman & Hall/CRC data mining and knowledge discovery series, (Editors: Srivastava, A. N. and Sahami, M.), CRC Press, Boca Raton, FL, USA, June 2009 (inbook)

Web DOI [BibTex]

Web DOI [BibTex]


Semi-supervised subspace analysis of human functional magnetic resonance imaging data

Shelton, J., Blaschko, M., Bartels, A.

(185), Max Planck Institute for Biological Cybernetics, Tübingen, Germany, May 2009 (techreport)

Abstract
Kernel Canonical Correlation Analysis is a very general technique for subspace learning that incorporates PCA and LDA as special cases. Functional magnetic resonance imaging (fMRI) acquired data is naturally amenable to these techniques as data are well aligned. fMRI data of the human brain is a particularly interesting candidate. In this study we implemented various supervised and semi-supervised versions of KCCA on human fMRI data, with regression to single- and multi-variate labels (corresponding to video content subjects viewed during the image acquisition). In each variate condition, the semi-supervised variants of KCCA performed better than the supervised variants, including a supervised variant with Laplacian regularization. We additionally analyze the weights learned by the regression in order to infer brain regions that are important to different types of visual processing.

PDF [BibTex]

PDF [BibTex]


Estimating Critical Stimulus Features from Psychophysical Data: The Decision-Image Technique Applied to Human Faces

Macke, J., Wichmann, F.

Journal of Vision, 9(8):31, 9th Annual Meeting of the Vision Sciences Society (VSS), August 2009 (poster)

Abstract
One of the main challenges in the sensory sciences is to identify the stimulus features on which the sensory systems base their computations: they are a pre-requisite for computational models of perception. We describe a technique---decision-images--- for extracting critical stimulus features based on logistic regression. Rather than embedding the stimuli in noise, as is done in classification image analysis, we want to infer the important features directly from physically heterogeneous stimuli. A Decision-image not only defines the critical region-of-interest within a stimulus but is a quantitative template which defines a direction in stimulus space. Decision-images thus enable the development of predictive models, as well as the generation of optimized stimuli for subsequent psychophysical investigations. Here we describe our method and apply it to data from a human face discrimination experiment. We show that decision-images are able to predict human responses not only in terms of overall percent correct but are able to predict, for individual observers, the probabilities with which individual faces are (mis-) classified. We then test the predictions of the models using optimized stimuli. Finally, we discuss possible generalizations of the approach and its relationships with other models.

Web DOI [BibTex]

Web DOI [BibTex]


A PAC-Bayesian Approach to Structure Learning

Seldin, Y.

Biologische Kybernetik, The Hebrew University of Jerusalem, Israel, September 2009 (phdthesis)

PDF [BibTex]

PDF [BibTex]


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

Lampert, C.

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

Web [BibTex]

Web [BibTex]


Efficient Bregman Range Search

Cayton, L.

In Advances in Neural Information Processing Systems 22, pages: 243-251, (Editors: Bengio, Y. , D. Schuurmans, J. Lafferty, C. Williams, A. Culotta), Curran, Red Hook, NY, USA, 23rd Annual Conference on Neural Information Processing Systems (NIPS), 2009 (inproceedings)

Abstract
We develop an algorithm for efficient range search when the notion of dissimilarity is given by a Bregman divergence. The range search task is to return all points in a potentially large database that are within some specified distance of a query. It arises in many learning algorithms such as locally-weighted regression, kernel density estimation, neighborhood graph-based algorithms, and in tasks like outlier detection and information retrieval. In metric spaces, efficient range search-like algorithms based on spatial data structures have been deployed on a variety of statistical tasks. Here we describe an algorithm for range search for an arbitrary Bregman divergence. This broad class of dissimilarity measures includes the relative entropy, Mahalanobis distance, Itakura-Saito divergence, and a variety of matrix divergences. Metric methods cannot be directly applied since Bregman divergences do not in general satisfy the triangle inequality. We derive geometric properties of Bregman divergences that yield an efficient algorithm for range search based on a recently proposed space decomposition for Bregman divergences.

PDF Web Project Page [BibTex]

PDF Web Project Page [BibTex]


Motor Control and Learning in Table Tennis

Mülling, K.

Eberhard Karls Universität Tübingen, Gerrmany, 2009 (diplomathesis)

[BibTex]

[BibTex]


Hierarchical Clustering and Density Estimation Based on k-nearest-neighbor graphs

Drewe, P.

Eberhard Karls Universität Tübingen, Germany, 2009 (diplomathesis)

[BibTex]

[BibTex]


mGene: accurate SVM-based gene finding with an application to nematode genomes

Schweikert, G., Zien, A., Zeller, G., Behr, J., Dieterich, C., Ong, C., Philips, P., De Bona, F., Hartmann, L., Bohlen, A., Krüger, N., Sonnenburg, S., Rätsch, G.

Genome Research, 19(11):2133-43, 2009 (article)

Abstract
We present a highly accurate gene-prediction system for eukaryotic genomes, called mGene. It combines in an unprecedented manner the flexibility of generalized hidden Markov models (gHMMs) with the predictive power of modern machine learning methods, such as Support Vector Machines (SVMs). Its excellent performance was proved in an objective competition based on the genome of the nematode Caenorhabditis elegans. Considering the average of sensitivity and specificity, the developmental version of mGene exhibited the best prediction performance on nucleotide, exon, and transcript level for ab initio and multiple-genome gene-prediction tasks. The fully developed version shows superior performance in 10 out of 12 evaluation criteria compared with the other participating gene finders, including Fgenesh++ and Augustus. An in-depth analysis of mGene's genome-wide predictions revealed that approximately 2200 predicted genes were not contained in the current genome annotation. Testing a subset of 57 of these genes by RT-PCR and sequencing, we confirmed expression for 24 (42%) of them. mGene missed 300 annotated genes, out of which 205 were unconfirmed. RT-PCR testing of 24 of these genes resulted in a success rate of merely 8%. These findings suggest that even the gene catalog of a well-studied organism such as C. elegans can be substantially improved by mGene's predictions. We also provide gene predictions for the four nematodes C. briggsae, C. brenneri, C. japonica, and C. remanei. Comparing the resulting proteomes among these organisms and to the known protein universe, we identified many species-specific gene inventions. In a quality assessment of several available annotations for these genomes, we find that mGene's predictions are most accurate.

DOI Project Page [BibTex]

DOI Project Page [BibTex]


Learning Probabilistic Models via Bayesian Inverse Planning

Boularias, A., Chaib-Draa, B.

NIPS Workshop on Probabilistic Approaches for Robotics and Control, December 2009 (poster)

PDF Web [BibTex]

PDF Web [BibTex]


Qualia: The Geometry of Integrated Information

Balduzzi, D., Tononi, G.

PLoS Computational Biology, 5(8):1-24, August 2009 (article)

Abstract
According to the integrated information theory, the quantity of consciousness is the amount of integrated information generated by a complex of elements, and the quality of experience is specified by the informational relationships it generates. This paper outlines a framework for characterizing the informational relationships generated by such systems. Qualia space (Q) is a space having an axis for each possible state (activity pattern) of a complex. Within Q, each submechanism specifies a point corresponding to a repertoire of system states. Arrows between repertoires in Q define informational relationships. Together, these arrows specify a quale—a shape that completely and univocally characterizes the quality of a conscious experience. Φ— the height of this shape—is the quantity of consciousness associated with the experience. Entanglement measures how irreducible informational relationships are to their component relationships, specifying concepts and modes. Several corollaries follow from these premises. The quale is determined by both the mechanism and state of the system. Thus, two different systems having identical activity patterns may generate different qualia. Conversely, the same quale may be generated by two systems that differ in both activity and connectivity. Both active and inactive elements specify a quale, but elements that are inactivated do not. Also, the activation of an element affects experience by changing the shape of the quale. The subdivision of experience into modalities and submodalities corresponds to subshapes in Q. In principle, different aspects of experience may be classified as different shapes in Q, and the similarity between experiences reduces to similarities between shapes. Finally, specific qualities, such as the “redness” of red, while generated by a local mechanism, cannot be reduced to it, but require considering the entire quale. Ultimately, the present framework may offer a principled way for translating qualitative properties of experience into mathematics.

Web DOI [BibTex]

Web DOI [BibTex]


Causality Discovery with Additive Disturbances: An Information-Theoretical Perspective

Zhang, K., Hyvärinen, A.

In Machine Learning and Knowledge Discovery in Databases, pages: 570-585, (Editors: Buntine, W. , M. Grobelnik, D. Mladenić, J. Shawe-Taylor ), Springer, Berlin, Germany, European Conference on Machine Learning and Knowledge Discovery in Databases: Part II (ECML PKDD '09), September 2009 (inproceedings)

Abstract
We consider causally sufficient acyclic causal models in which the relationship among the variables is nonlinear while disturbances have linear effects, and show that three principles, namely, the causal Markov condition (together with the independence between each disturbance and the corresponding parents), minimum disturbance entropy, and mutual independence of the disturbances, are equivalent. This motivates new and more efficient methods for some causal discovery problems. In particular, we propose to use multichannel blind deconvolution, an extension of independent component analysis, to do Granger causality analysis with instantaneous effects. This approach gives more accurate estimates of the parameters and can easily incorporate sparsity constraints. For additive disturbance-based nonlinear causal discovery, we first make use of the conditional independence relationships to obtain the equivalence class; undetermined causal directions are then found by nonlinear regression and pairwise independence tests. This avoids the brute-force search and greatly reduces the computational load.

PDF PDF DOI [BibTex]

PDF PDF DOI [BibTex]


A Novel Context-Sensitive Semisupervised SVM Classifier Robust to Mislabeled Training Samples

Bruzzone, L., Persello, C.

IEEE Transactions on Geoscience and Remote Sensing, 47(7):2142-2154, July 2009 (article)

Abstract
This paper presents a novel context-sensitive semisupervised support vector machine (CS4VM) classifier, which is aimed at addressing classification problems where the available training set is not fully reliable, i.e., some labeled samples may be associated to the wrong information class (mislabeled patterns). Unlike standard context-sensitive methods, the proposed CS4VM classifier exploits the contextual information of the pixels belonging to the neighborhood system of each training sample in the learning phase to improve the robustness to possible mislabeled training patterns. This is achieved according to both the design of a semisupervised procedure and the definition of a novel contextual term in the cost function associated with the learning of the classifier. In order to assess the effectiveness of the proposed CS4VM and to understand the impact of the addressed problem in real applications, we also present an extensive experimental analysis carried out on training sets that include different percentages of mislabeled patterns having different distributions on the classes. In the analysis, we also study the robustness to mislabeled training patterns of some widely used supervised and semisupervised classification algorithms (i.e., conventional support vector machine (SVM), progressive semisupervised SVM, maximum likelihood, and k-nearest neighbor). Results obtained on a very high resolution image and on a medium resolution image confirm both the robustness and the effectiveness of the proposed CS4VM with respect to standard classification algorithms and allow us to derive interesting conclusions on the effects of mislabeled patterns on different classifiers.

Web DOI [BibTex]

Web DOI [BibTex]


Expectation Propagation on the Maximum of Correlated Normal Variables

Hennig, P.

Cavendish Laboratory: University of Cambridge, July 2009 (techreport)

Abstract
Many inference problems involving questions of optimality ask for the maximum or the minimum of a finite set of unknown quantities. This technical report derives the first two posterior moments of the maximum of two correlated Gaussian variables and the first two posterior moments of the two generating variables (corresponding to Gaussian approximations minimizing relative entropy). It is shown how this can be used to build a heuristic approximation to the maximum relationship over a finite set of Gaussian variables, allowing approximate inference by Expectation Propagation on such quantities.

Web [BibTex]

Web [BibTex]


Protein Functional Class Prediction With a Combined Graph

Shin, H., Tsuda, K., Schölkopf, B.

Expert Systems with Applications, 36(2):3284-3292, March 2009 (article)

Abstract
In bioinformatics, there exist multiple descriptions of graphs for the same set of genes or proteins. For instance, in yeast systems, graph edges can represent different relationships such as protein–protein interactions, genetic interactions, or co-participation in a protein complex, etc. Relying on similarities between nodes, each graph can be used independently for prediction of protein function. However, since different graphs contain partly independent and partly complementary information about the problem at hand, one can enhance the total information extracted by combining all graphs. In this paper, we propose a method for integrating multiple graphs within a framework of semi-supervised learning. The method alternates between minimizing the objective function with respect to network output and with respect to combining weights. We apply the method to the task of protein functional class prediction in yeast. The proposed method performs significantly better than the same algorithm trained on any singl e graph.

Web DOI [BibTex]

Web DOI [BibTex]


Falsificationism and Statistical Learning Theory: Comparing the Popper and Vapnik-Chervonenkis Dimensions

Corfield, D., Schölkopf, B., Vapnik, V.

Journal for General Philosophy of Science, 40(1):51-58, July 2009 (article)

Abstract
We compare Karl Popper’s ideas concerning the falsifiability of a theory with similar notions from the part of statistical learning theory known as VC-theory. Popper’s notion of the dimension of a theory is contrasted with the apparently very similar VC-dimension. Having located some divergences, we discuss how best to view Popper’s work from the perspective of statistical learning theory, either as a precursor or as aiming to capture a different learning activity.

PDF DOI [BibTex]

PDF DOI [BibTex]


Beamforming in Noninvasive Brain-Computer Interfaces

Grosse-Wentrup, M., Liefhold, C., Gramann, K., Buss, M.

IEEE Transactions on Biomedical Engineering, 56(4):1209-1219, April 2009 (article)

Abstract
Spatial filtering (SF) constitutes an integral part of building EEG-based brain–computer interfaces (BCIs). Algorithms frequently used for SF, such as common spatial patterns (CSPs) and independent component analysis, require labeled training data for identifying filters that provide information on a subject‘s intention, which renders these algorithms susceptible to overfitting on artifactual EEG components. In this study, beamforming is employed to construct spatial filters that extract EEG sources originating within predefined regions of interest within the brain. In this way, neurophysiological knowledge on which brain regions are relevant for a certain experimental paradigm can be utilized to construct unsupervised spatial filters that are robust against artifactual EEG components. Beamforming is experimentally compared with CSP and Laplacian spatial filtering (LP) in a two-class motor-imagery paradigm. It is demonstrated that beamforming outperforms CSP and LP on noisy datasets, while CSP and beamforming perform almost equally well on datasets with few artifactual trials. It is concluded that beamforming constitutes an alternative method for SF that might be particularly useful for BCIs used in clinical settings, i.e., in an environment where artifact-free datasets are difficult to obtain.

PDF Web DOI Project Page [BibTex]

PDF Web DOI Project Page [BibTex]


Center-surround patterns emerge as optimal predictors for human saccade targets

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

Journal of Vision, 9(5:7):1-15, May 2009 (article)

Abstract
The human visual system is foveated, that is, outside the central visual field resolution and acuity drop rapidly. Nonetheless much of a visual scene is perceived after only a few saccadic eye movements, suggesting an effective strategy for selecting saccade targets. It has been known for some time that local image structure at saccade targets influences the selection process. However, the question of what the most relevant visual features are is still under debate. Here we show that center-surround patterns emerge as the optimal solution for predicting saccade targets from their local image structure. The resulting model, a one-layer feed-forward network, is surprisingly simple compared to previously suggested models which assume much more complex computations such as multi-scale processing and multiple feature channels. Nevertheless, our model is equally predictive. Furthermore, our findings are consistent with neurophysiological hardware in the superior colliculus. Bottom-up visual saliency may thus not be computed cortically as has been thought previously.

PDF DOI Project Page [BibTex]


Constructing Sparse Kernel Machines Using Attractors

Lee, D., Jung, K., Lee, J.

IEEE Transactions on Neural Networks, 20(4):721-729, April 2009 (article)

Abstract
In this brief, a novel method that constructs a sparse kernel machine is proposed. The proposed method generates attractors as sparse solutions from a built-in kernel machine via a dynamical system framework. By readjusting the corresponding coefficients and bias terms, a sparse kernel machine that approximates a conventional kernel machine is constructed. The simulation results show that the constructed sparse kernel machine improves the efficiency of testing phase while maintaining comparable test error.

Web DOI [BibTex]

Web DOI [BibTex]


Optimal construction of k-nearest-neighbor graphs for identifying noisy clusters

Maier, M., Hein, M., von Luxburg, U.

Theoretical Computer Science, 410(19):1749-1764, April 2009 (article)

Abstract
We study clustering algorithms based on neighborhood graphs on a random sample of data points. The question we ask is how such a graph should be constructed in order to obtain optimal clustering results. Which type of neighborhood graph should one choose, mutual k-nearest-neighbor or symmetric k-nearest-neighbor? What is the optimal parameter k? In our setting, clusters are defined as connected components of the t-level set of the underlying probability distribution. Clusters are said to be identified in the neighborhood graph if connected components in the graph correspond to the true underlying clusters. Using techniques from random geometric graph theory, we prove bounds on the probability that clusters are identified successfully, both in a noise-free and in a noisy setting. Those bounds lead to several conclusions. First, k has to be chosen surprisingly high (rather of the order n than of the order logn) to maximize the probability of cluster identification. Secondly, the major difference between the mutual and the symmetric k-nearest-neighbor graph occurs when one attempts to detect the most significant cluster only.

PDF PDF DOI [BibTex]


Policy Search for Motor Primitives

Peters, J., Kober, J.

KI - Zeitschrift K{\"u}nstliche Intelligenz, 23(3):38-40, August 2009 (article)

Abstract
Many motor skills in humanoid robotics can be learned using parametrized motor primitives from demonstrations. However, most interesting motor learning problems require self-improvement often beyond the reach of current reinforcement learning methods due to the high dimensionality of the state-space. We develop an EM-inspired algorithm applicable to complex motor learning tasks. We compare this algorithm to several well-known parametrized policy search methods and show that it outperforms them. We apply it to motor learning problems and show that it can learn the complex Ball-in-a-Cup task using a real Barrett WAM robot arm.

Web [BibTex]

Web [BibTex]


Learning Taxonomies by Dependence Maximization

Blaschko, M., Gretton, A.

In Advances in neural information processing systems 21, pages: 153-160, (Editors: Koller, D. , D. Schuurmans, Y. Bengio, L. Bottou), Curran, Red Hook, NY, USA, Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS), June 2009 (inproceedings)

Abstract
We introduce a family of unsupervised algorithms, numerical taxonomy clustering, to simultaneously cluster data, and to learn a taxonomy that encodes the relationship between the clusters. The algorithms work by maximizing the dependence between the taxonomy and the original data. The resulting taxonomy is a more informative visualization of complex data than simple clustering; in addition, taking into account the relations between different clusters is shown to substantially improve the quality of the clustering, when compared with state-ofthe-art algorithms in the literature (both spectral clustering and a previous dependence maximization approach). We demonstrate our algorithm on image and text data.

PDF Web [BibTex]