The problem of learning a semantic representation of a text document from data is addressed, in the situation where a corpus of unlabeled paired documents is available, each pair being formed by a short English documentand its French translation. This representation can then be used for any retrieval, categorization or clustering task, both in a standard andin a cross-lingual setting. By using kernel functions, in this case simple bag-of-words inner products, each part of the corpus is mapped to a high-dimensional space. The correlations between the two spaces are then learnt by using kernel Canonical Correlation Analysis. A set of directions is found in the first and in the second space that are maximally correlated.Since we assume the two representations are completely independentapart from the semantic content, any correlation between them should reflect some semantic similarity. Certain patterns of English words that relate to a specific meaning should correlate with certain patternsof French words corresponding to the same meaning, across the corpus. Using the semantic representation obtained in this way we first demonstrate that the correlations detected between the two versions of the corpus are significantly higher than random, and hence that a representation basedon such features does capture statistical patterns that should reflect semantic information. Then we use such representation both in cross-language and in single-language retrieval tasks, observing performance that is consistently and significantly superior to LSI on the same data.

We introduce the notion of Morton-style factorial coding and illustrate how it may help understand information integration and perceptual coding inthe brain. We show that by focusing on average responses one may miss the existence of factorial coding mechanisms that become only apparent when analyzing spike count histograms. We show evidence suggesting that the classical/nonclassical receptive field organization in the cortex effectively enforces the development of Morton-style factorial codes. This may provide some cues to help understand perceptual coding inthe brain and to develop new unsupervised learning algorithms. While methods like ICA (Bell & Sejnowski, 1997) develop independent codes, in Morton-style coding the goal is to make two or more external aspects of the world become independent when conditioning on internal representations.

We extend recent work on the connection between loopy belief propagation and the Bethe free energy. Constrained minimization of the Bethe free energy can be turned into an unconstrained saddle-point problem. Both converging double-loop algorithms and standard loopy belief propagation can be interpreted asattempts to solve this saddle-point problem. Stability analysis then leads us to conclude that stable fixed points of loopy belief propagation must be (local) minima of the Bethe free energy. Perhaps surprisingly, the converse need not be the case: minima can be unstable fixed points. We illustrate this with an example and discuss implications.

We consider the problem of illusory or artefactual structure from the visualisation ofhigh-dimensional structureless data. In particular we examine the role of the distance metric in the use of topographic mappings based on the statistical field of multidimensional scaling. We show that the use of a squared Euclidean metric (i.e. the SSTRESS measure) gives rise to an annular structure when the input data is drawn from a highdimensional isotropicdistribution, and we provide a theoretical justification for this observation.

The extraction of a single high-quality image from a set of lowresolution imagesis an important problem which arises in fields such as remote sensing, surveillance, medical imaging and the extraction ofstill images from video. Typical approaches are based on the use of cross-correlation to register the images followed by the inversion of the transformation from the unknown high resolution imageto the observed low resolution images, using regularization toresolve the ill-posed nature of the inversion process. In this paper we develop a Bayesian treatment of the super-resolution problem in which the likelihood function for the image registration parametersis based on a marginalization over the unknown high-resolution image. This approach allows us to estimate the unknown point spread function, and is rendered tractable through the introduction of a Gaussian process prior over images. Results indicate a significant improvement over techniques based on MAP (maximum a-posteriori) point optimization of the high resolution image and associated registration parameters. 1 Introduction The task in super-resolution is to combine a set of low resolution images of the same scene in order to obtain a single image of higher resolution. Provided the individual low resolution images have sub-pixel displacements relative to each other, it is possible to extract high frequency details of the scene well beyond the Nyquist limit of the individual source images.

The responses of cortical sensory neurons are notoriously variable, with the number of spikes evoked by identical stimuli varying significantly from trial to trial. This variability is most often interpreted as'noise', purely detrimental to the sensory system. In this paper, we propose an alternative viewin which the variability is related to the uncertainty, about world parameters, which is inherent in the sensory stimulus. Specifically, theresponses of a population of neurons are interpreted as stochastic samples from the posterior distribution in a latent variable model. In addition to giving theoretical arguments supporting such a representational scheme,we provide simulations suggesting how some aspects of response variability might be understood in this framework.

This paper presents a novel Hidden Markov Model architecture to model the joint probability of pairs of asynchronous sequences describing thesame event. It is based on two other Markovian models, namely Asynchronous Input/ Output Hidden Markov Models and Pair Hidden Markov Models. An EM algorithm to train the model is presented, as well as a Viterbi decoder that can be used to obtain theoptimal state sequence as well as the alignment between the two sequences. The model has been tested on an audiovisual speech recognition task using the M2VTS database and yielded robust performances under various noise conditions. 1 Introduction Hidden Markov Models (HMMs) are statistical tools that have been used successfully inthe last 30 years to model difficult tasks such as speech recognition [6) or biological sequence analysis [4). They are very well suited to handle discrete of continuous sequencesof varying sizes.

Monaural speech separation has been studied in previous systems that incorporate auditory scene analysis principles. A major problem for these systems is their inability to deal with speech in the highfrequency range.Psychoacoustic evidence suggests that different perceptual mechanisms are involved in handling resolved and unresolved harmonics. Motivated by this, we propose a model for monaural separation that deals with low-frequency and highfrequency signalsdifferently. For resolved harmonics, our model generates segments based on temporal continuity and cross-channel correlation, and groups them according to periodicity. For unresolved harmonics, the model generates segments based on amplitude modulation (AM) in addition to temporal continuity and groups them according to AM repetition rates derived from sinusoidal modeling. Underlying the separation process is a pitch contour obtained according to psychoacoustic constraints. Our model is systematically evaluated, and it yields substantially better performance than previous systems, especially in the high-frequency range.

We consider loopy belief propagation for approximate inference in probabilistic graphicalmodels. A limitation of the standard algorithm is that clique marginals are computed as if there were no loops in the graph. To overcome this limitation, we introduce fractional belief propagation. Fractional belief propagation is formulated in terms of a family of approximate freeenergies, which includes the Bethe free energy and the naive mean-field free as special cases. Using the linear response correction ofthe clique marginals, the scale parameters can be tuned. Simulation results illustrate the potential merits of the approach.

Language acquisition is a special kind of learning problem because the outcome of learning of one generation is the input for the next. That makes it possible for languages to adapt to the particularities of the learner. In this paper, I show that this type of language change has important consequences for models of the evolution and acquisition of syntax. 1 The Language Acquisition Problem For both artificial systems and nonhuman animals, learning the syntax of natural languages is a notoriously hard problem. All healthy human infants, in contrast, learn any of the approximately 6000 human languages rapidly, accurately and spontaneously. Anyexplanation of how they accomplish this difficult task must specify the (innate) inductive bias that human infants bring to bear, and the input data that is available to them. Traditionally, the inductive bias is termed - somewhat unfortunately -"Universal Grammar", and the input data "primary linguistic data". Over the last 30 years or so, a view on the acquisition of the syntax of natural language has become popular that has put much emphasis on the innate machinery. In this view, that one can call the "Principles and Parameters" model, the Universal Grammar specifies most aspects of syntax in great detail [e.g.