Header logo is ei


2002


no image

no image
Stability and Generalization

Bousquet, O., Elisseeff, A.

Journal of Machine Learning Research, 2, pages: 499-526, 2002 (article)

Abstract
We define notions of stability for learning algorithms and show how to use these notions to derive generalization error bounds based on the empirical error and the leave-one-out error. The methods we use can be applied in the regression framework as well as in the classification one when the classifier is obtained by thresholding a real-valued function. We study the stability properties of large classes of learning algorithms such as regularization based algorithms. In particular we focus on Hilbert space regularization and Kullback-Leibler regularization. We demonstrate how to apply the results to SVM for regression and classification.

PDF PostScript [BibTex]

PDF PostScript [BibTex]


no image
Subspace information criterion for non-quadratic regularizers – model selection for sparse regressors

Tsuda, K., Sugiyama, M., Müller, K.

IEEE Trans Neural Networks, 13(1):70-80, 2002 (article)

PDF [BibTex]

PDF [BibTex]


no image
Modeling splicing sites with pairwise correlations

Arita, M., Tsuda, K., Asai, K.

Bioinformatics, 18(Suppl 2):27-34, 2002 (article)

PDF [BibTex]

PDF [BibTex]


no image
Perfusion Quantification using Gaussian Process Deconvolution

Andersen, IK., Szymkowiak, A., Rasmussen, CE., Hanson, LG., Marstrand, JR., Larsson, HBW., Hansen, LK.

Magnetic Resonance in Medicine, (48):351-361, 2002 (article)

Abstract
The quantification of perfusion using dynamic susceptibility contrast MR imaging requires deconvolution to obtain the residual impulse-response function (IRF). Here, a method using a Gaussian process for deconvolution, GPD, is proposed. The fact that the IRF is smooth is incorporated as a constraint in the method. The GPD method, which automatically estimates the noise level in each voxel, has the advantage that model parameters are optimized automatically. The GPD is compared to singular value decomposition (SVD) using a common threshold for the singular values and to SVD using a threshold optimized according to the noise level in each voxel. The comparison is carried out using artificial data as well as using data from healthy volunteers. It is shown that GPD is comparable to SVD variable optimized threshold when determining the maximum of the IRF, which is directly related to the perfusion. GPD provides a better estimate of the entire IRF. As the signal to noise ratio increases or the time resolution of the measurements increases, GPD is shown to be superior to SVD. This is also found for large distribution volumes.

PDF PostScript [BibTex]

PDF PostScript [BibTex]


no image
Tracking a Small Set of Experts by Mixing Past Posteriors

Bousquet, O., Warmuth, M.

Journal of Machine Learning Research, 3, pages: 363-396, (Editors: Long, P.), 2002 (article)

Abstract
In this paper, we examine on-line learning problems in which the target concept is allowed to change over time. In each trial a master algorithm receives predictions from a large set of n experts. Its goal is to predict almost as well as the best sequence of such experts chosen off-line by partitioning the training sequence into k+1 sections and then choosing the best expert for each section. We build on methods developed by Herbster and Warmuth and consider an open problem posed by Freund where the experts in the best partition are from a small pool of size m. Since k >> m, the best expert shifts back and forth between the experts of the small pool. We propose algorithms that solve this open problem by mixing the past posteriors maintained by the master algorithm. We relate the number of bits needed for encoding the best partition to the loss bounds of the algorithms. Instead of paying log n for choosing the best expert in each section we first pay log (n choose m) bits in the bounds for identifying the pool of m experts and then log m bits per new section. In the bounds we also pay twice for encoding the boundaries of the sections.

PDF PostScript [BibTex]

PDF PostScript [BibTex]


no image
A femoral arteriovenous shunt facilitates arterial whole blood sampling in animals

Weber, B., Burger, C., Biro, P., Buck, A.

Eur J Nucl Med Mol Imaging, 29, pages: 319-323, 2002 (article)

[BibTex]

[BibTex]


no image
Contrast discrimination with pulse-trains in pink noise

Henning, G., Bird, C., Wichmann, F.

Journal of the Optical Society of America A, 19(7), pages: 1259-1266, 2002 (article)

Abstract
Detection performance was measured with sinusoidal and pulse-train gratings. Although the 2.09-c/deg pulse-train, or line gratings, contained at least 8 harmonics all at equal contrast, they were no more detectable than their most detectable component. The addition of broadband pink noise designed to equalize the detectability of the components of the pulse train made the pulse train about a factor of four more detectable than any of its components. However, in contrast-discrimination experiments, with a pedestal or masking grating of the same form and phase as the signal and 15% contrast, the noise did not affect the discrimination performance of the pulse train relative to that obtained with its sinusoidal components. We discuss the implications of these observations for models of early vision in particular the implications for possible sources of internal noise.

PDF [BibTex]

PDF [BibTex]


no image
Choosing Multiple Parameters for Support Vector Machines

Chapelle, O., Vapnik, V., Bousquet, O., Mukherjee, S.

Machine Learning, 46(1):131-159, 2002 (article)

Abstract
The problem of automatically tuning multiple parameters for pattern recognition Support Vector Machines (SVM) is considered. This is done by minimizing some estimates of the generalization error of SVMs using a gradient descent algorithm over the set of parameters. Usual methods for choosing parameters, based on exhaustive search become intractable as soon as the number of parameters exceeds two. Some experimental results assess the feasibility of our approach for a large number of parameters (more than 100) and demonstrate an improvement of generalization performance.

PDF PostScript [BibTex]

PDF PostScript [BibTex]

1999


no image
Lernen mit Kernen: Support-Vektor-Methoden zur Analyse hochdimensionaler Daten

Schölkopf, B., Müller, K., Smola, A.

Informatik - Forschung und Entwicklung, 14(3):154-163, September 1999 (article)

Abstract
We describe recent developments and results of statistical learning theory. In the framework of learning from examples, two factors control generalization ability: explaining the training data by a learning machine of a suitable complexity. We describe kernel algorithms in feature spaces as elegant and efficient methods of realizing such machines. Examples thereof are Support Vector Machines (SVM) and Kernel PCA (Principal Component Analysis). More important than any individual example of a kernel algorithm, however, is the insight that any algorithm that can be cast in terms of dot products can be generalized to a nonlinear setting using kernels. Finally, we illustrate the significance of kernel algorithms by briefly describing industrial and academic applications, including ones where we obtained benchmark record results.

PDF PDF DOI [BibTex]

1999

PDF PDF DOI [BibTex]


no image
Input space versus feature space in kernel-based methods

Schölkopf, B., Mika, S., Burges, C., Knirsch, P., Müller, K., Rätsch, G., Smola, A.

IEEE Transactions On Neural Networks, 10(5):1000-1017, September 1999 (article)

Abstract
This paper collects some ideas targeted at advancing our understanding of the feature spaces associated with support vector (SV) kernel functions. We first discuss the geometry of feature space. In particular, we review what is known about the shape of the image of input space under the feature space map, and how this influences the capacity of SV methods. Following this, we describe how the metric governing the intrinsic geometry of the mapped surface can be computed in terms of the kernel, using the example of the class of inhomogeneous polynomial kernels, which are often used in SV pattern recognition. We then discuss the connection between feature space and input space by dealing with the question of how one can, given some vector in feature space, find a preimage (exact or approximate) in input space. We describe algorithms to tackle this issue, and show their utility in two applications of kernel methods. First, we use it to reduce the computational complexity of SV decision functions; second, we combine it with the kernel PCA algorithm, thereby constructing a nonlinear statistical denoising technique which is shown to perform well on real-world data.

Web DOI [BibTex]

Web DOI [BibTex]


no image
p73 and p63 are homotetramers capable of weak heterotypic interactions with each other but not with p53.

Davison, T., Vagner, C., Kaghad, M., Ayed, A., Caput, D., CH, ..

Journal of Biological Chemistry, 274(26):18709-18714, June 1999 (article)

Abstract
Mutations in the p53 tumor suppressor gene are the most frequent genetic alterations found in human cancers. Recent identification of two human homologues of p53 has raised the prospect of functional interactions between family members via a conserved oligomerization domain. Here we report in vitro and in vivo analysis of homo- and hetero-oligomerization of p53 and its homologues, p63 and p73. The oligomerization domains of p63 and p73 can independently fold into stable homotetramers, as previously observed for p53. However, the oligomerization domain of p53 does not associate with that of either p73 or p63, even when p53 is in 15-fold excess. On the other hand, the oligomerization domains of p63 and p73 are able to weakly associate with one another in vitro. In vivo co-transfection assays of the ability of p53 and its homologues to activate reporter genes showed that a DNA-binding mutant of p53 was not able to act in a dominant negative manner over wild-type p73 or p63 but that a p73 mutant could inhibit the activity of wild-type p63. These data suggest that mutant p53 in cancer cells will not interact with endogenous or exogenous p63 or p73 via their respective oligomerization domains. It also establishes that the multiple isoforms of p63 as well as those of p73 are capable of interacting via their common oligomerization domain.

Web [BibTex]

Web [BibTex]


no image
Spatial Learning and Localization in Animals: A Computational Model and Its Implications for Mobile Robots

Balakrishnan, K., Bousquet, O., Honavar, V.

Adaptive Behavior, 7(2):173-216, 1999 (article)

[BibTex]


no image
SVMs for Histogram Based Image Classification

Chapelle, O., Haffner, P., Vapnik, V.

IEEE Transactions on Neural Networks, (9), 1999 (article)

Abstract
Traditional classification approaches generalize poorly on image classification tasks, because of the high dimensionality of the feature space. This paper shows that Support Vector Machines (SVM) can generalize well on difficult image classification problems where the only features are high dimensional histograms. Heavy-tailed RBF kernels of the form $K(mathbf{x},mathbf{y})=e^{-rhosum_i |x_i^a-y_i^a|^{b}}$ with $aleq 1$ and $b leq 2$ are evaluated on the classification of images extracted from the Corel Stock Photo Collection and shown to far outperform traditional polynomial or Gaussian RBF kernels. Moreover, we observed that a simple remapping of the input $x_i rightarrow x_i^a$ improves the performance of linear SVMs to such an extend that it makes them, for this problem, a valid alternative to RBF kernels.

GZIP [BibTex]

GZIP [BibTex]