An image is often represented by a set of detected features. We get an enormous compression by representing images in this way. Furthermore, weget a representation which is little affected by small amounts of noise in the image. However, features are typically chosen in an ad hoc manner.

We first describe a hierarchical, generative model that can be viewed as a nonlinear generalisation of factor analysis and can be implemented in a neural network. The model performs perceptual inferencein a probabilistically consistent manner by using top-down, bottom-up and lateral connections. These connections can be learned using simple rules that require only locally available information.We then show how to incorporate lateral connections intothe generative model. The model extracts a sparse, distributed, hierarchical representation of depth from simplified random-dot stereograms and the localised disparity detectors in the first hidden layer form a topographic map. When presented with image patches from natural scenes, the model develops topographically organisedlocal feature detectors.

We explain how the training data can be separated into clean information andunexplainable noise. Analogous to the data, the neural network is separated into a time invariant structure used for forecasting, and a noisy part. We propose a unified theory connecting the optimization algorithms forcleaning and learning together with algorithms that control the data noise and the parameter noise. The combined algorithm allows a data-driven local control of the liability of the network parameters and therefore an improvement in generalization. The approach is proven to be very useful at the task of forecasting the German bond market.

Each chart is primarily divided into the three major noise conditions, cf.

We derive a learning algorithm for inferring an overcomplete basis by viewing it as probabilistic model of the observed data.

We present a new approach to reinforcement learning in which the policies consideredby the learning process are constrained by hierarchies of partially specified machines. This allows for the use of prior knowledge to reduce the search space and provides a framework in which knowledge can be transferred across problems and in which component solutions can be recombined to solve larger and more complicated problems. Our approach can be seen as providing a link between reinforcement learning and"behavior-based" or "teleo-reactive" approaches to control. We present provably convergent algorithms for problem-solving and learning withhierarchical machines and demonstrate their effectiveness on a problem with several thousand states.

It is especially suited for speech and image data which in many applieations have to be transmitted under low bandwidth/high noise level conditions. Followingthe idea of (Farvardin, 1990) and (Luttrell, 1989) of jointly optimizing the codebook and the data representation w.r.t. to a given channel noise we apply a deterministic annealingscheme (Rose, 1990; Buhmann, 1997) to the problem and develop a An Annealed Self-Organizing Map for Source Channel Coding 431 soft topographic vector quantization algorithm (STVQ) (cf.

Friedman's combination rule is quite intuitive: assign to the class that wins the most pairwise comparisons.

The Natural abstract actions are to move from room to room. 1 Reinforcement Learning (MDP) Framework In reinforcement learning, a learning agent interacts with an environment at some discrete, lowest-level time scale t 0,1,2, ... On each time step, the agent perceives the state of the environment, St, and on that basis chooses a primitive action, at.

We consider the general problem of learning multi-category classification fromlabeled examples. We present experimental results for a nearest neighbor algorithm which actively selects samples from different pattern classes according to a querying rule instead of the a priori class probabilities. The amount of improvement of this query-based approach over the passive batch approach depends on the complexity of the Bayes rule. The principle on which this algorithm isbased is general enough to be used in any learning algorithm which permits a model-selection criterion and for which the error rate of the classifier is calculable in terms of the complexity of the model. 1 INTRODUCTION We consider the general problem of learning multi-category classification from labeled examples.In many practical learning settings the time or sample size available for training are limited. This may have adverse effects on the accuracy of the resulting classifier.For instance, in learning to recognize handwritten characters typical time limitation confines the training sample size to be of the order of a few hundred examples. It is important to make learning more efficient by obtaining only training data which contains significant information about the separability of the pattern classes thereby letting the learning algorithm participate actively in the sampling process. Querying for the class labels of specificly selected examples in the input space may lead to significant improvements in the generalization error (cf.