The problem of reinforcement learning in a non-Markov environment is explored using a dynamic Bayesian network, where conditional independence assumptions between random variables are compactly represented by network parameters. The parameters are learned online, and approximations are used to perform inference and to compute the optimal value function. The relative effects of inference and value function approximations on the quality of the final policy are investigated, by learning to solve a moderately difficult driving task. The two value function approximations, linear and quadratic, were found to perform similarly, but the quadratic model was more sensitive to initialization. Both performed below the level of human performance on the task. The dynamic Bayesian network performed comparably to a model using a localist hidden state representation, while requiring exponentially fewer parameters.

In the analysis of data recorded by optical imaging from intrinsic signals (measurement of changes of light reflectance from cortical tissue) the removal of noise and artifacts such as blood vessel patterns is a serious problem. Often bandpass filtering is used, but the underlying assumption that a spatial frequency exists, which separates the mapping component from other components (especially the global signal), is questionable. Here we propose alternative ways of processing optical imaging data, using blind source separation techniques based on the spatial decorre1ation of the data. We first perform benchmarks on artificial data in order to select the way of processing, which is most robust with respect to sensor noise. We then apply it to recordings of optical imaging experiments from macaque primary visual cortex. We show that our BSS technique is able to extract ocular dominance and orientation preference maps from single condition stacks, for data, where standard post-processing procedures fail. Artifacts, especially blood vessel patterns, can often be completely removed from the maps. In summary, our method for blind source separation using extended spatial decorrelation is a superior technique for the analysis of optical recording data.

We formulate the problem of retrieving images from visual databases as a problem of Bayesian inference. This leads to natural and effective solutions for two of the most challenging issues in the design of a retrieval system: providing support for region-based queries without requiring prior image segmentation, and accounting for user-feedback during a retrieval session. We present a new learning algorithm that relies on belief propagation to account for both positive and negative examples of the user's interests.

One of the open questions that remains is how to set the'tunable' parameters of an SVM algorithm: While methods for choosing the width of the kernel function and the noise parameter C (which controls how closely the training data are fitted) have been proposed [4, 5] (see also, very recently, [6]), the effect of the overall shape of the kernel function remains imperfectly understood [1]. Error bars (class probabilities) for SVM predictions - important for safety-critical applications, for example - are also difficult to obtain. In this paper I suggest that a probabilistic interpretation of SVMs could be used to tackle these problems. It shows that the SVM kernel defines a prior over functions on the input space, avoiding the need to think in terms of high-dimensional feature spaces. It also allows one to define quantities such as the evidence (likelihood) for a set of hyperparameters (C, kernel amplitude Ko etc). I give a simple approximation to the evidence which can then be maximized to set such hyperparameters. The evidence is sensitive to the values of C and Ko individually, in contrast to properties (such as cross-validation error) of the deterministic solution, which only depends on the product CKo. It can thfrefore be used to assign an unambiguous value to C, from which error bars can be derived.

Previous biophysical modeling work showed that nonlinear interactions among nearby synapses located on active dendritic trees can provide a large boost in the memory capacity of a cell (Mel, 1992a, 1992b). The aim of our present work is to quantify this boost by estimating the capacity of (1) a neuron model with passive dendritic integration where inputs are combined linearly across the entire cell followed by a single global threshold, and (2) an active dendrite model in which a threshold is applied separately to the output of each branch, and the branch subtotals are combined linearly. We focus here on the limiting case of binary-valued synaptic weights, and derive expressions which measure model capacity by estimating the number of distinct input-output functions available to both neuron types. We show that (1) the application of a fixed nonlinearity to each dendritic compartment substantially increases the model's flexibility, (2) for a neuron of realistic size, the capacity of the nonlinear cell can exceed that of the same-sized linear cell by more than an order of magnitude, and (3) the largest capacity boost occurs for cells with a relatively large number of dendritic subunits of relatively small size. We validated the analysis by empirically measuring memory capacity with randomized two-class classification problems, where a stochastic delta rule was used to train both linear and nonlinear models. We found that large capacity boosts predicted for the nonlinear dendritic model were readily achieved in practice.

We formulate a model for probability distributions on image spaces. We show that any distribution of images can be factored exactly into conditional distributions of feature vectors at one resolution (pyramid level) conditioned on the image information at lower resolutions. We would like to factor this over positions in the pyramid levels to make it tractable, but such factoring may miss long-range dependencies. To fix this, we introduce hidden class labels at each pixel in the pyramid. The result is a hierarchical mixture of conditional probabilities, similar to a hidden Markov model on a tree. The model parameters can be found with maximum likelihood estimation using the EM algorithm. We have obtained encouraging preliminary results on the problems of detecting various objects in SAR images and target recognition in optical aerial images. 1 Introduction

Spatial information comes in two forms: direct spatial information (for example, retinal position) and indirect temporal contiguity information, since objects encountered sequentially are in general spatially close. The acquisition of spatial information by a neural network is investigated here. Given a spatial layout of several objects, networks are trained on a prediction task. Networks using temporal sequences with no direct spatial information are found to develop internal representations that show distances correlated with distances in the external layout. The influence of spatial information is analyzed by providing direct spatial information to the system during training that is either consistent with the layout or inconsistent with it. This approach allows examination of the relative contributions of spatial and temporal contiguity.

Reinforcement learning in nonstationary environments is generally regarded as an important and yet difficult problem. This paper partially addresses the problem by formalizing a subclass of nonstationary environments. The environment model, called hidden-mode Markov decision process (HM-MDP), assumes that environmental changes are always confined to a small number of hidden modes.

In hyperspectral imagery one pixel typically consists of a mixture of the reflectance spectra of several materials, where the mixture coefficients correspond to the abundances of the constituting materials. We assume linear combinations of reflectance spectra with some additive normal sensor noise and derive a probabilistic MAP framework for analyzing hyperspectral data. As the material reflectance characteristics are not know a priori, we face the problem of unsupervised linear unmixing.

In this paper we will treat input selection for a radial basis function (RBF) like classifier within a Bayesian framework. We approximate the a-posteriori distribution over both model coefficients and input subsets by samples drawn with Gibbs updates and reversible jump moves. Using some public datasets, we compare the classification accuracy of the method with a conventional ARD scheme. These datasets are also used to infer the a-posteriori probabilities of different input subsets. 1 Introduction Methods that aim to determine relevance of inputs have always interested researchers in various communities. Classical feature subset selection techniques, as reviewed in [1], use search algorithms and evaluation criteria to determine one optimal subset.