Resumo em Inglês:

The World Graph theory developed the hypothesis that cognitive and motivational states interact. This paper describes NeWG, a hybrid neural network implementation of this theory as well as a modeling environment for the investigation of motivated spatial behavior. NeWG comprises a modified Fuzzy ART network, the START network, which incorporates the world graph properties to produce goal-oriented behavior. Neurophysiological data are then used to support a model of the rat’s cognitive map encoded as an internal world graph

Resumo em Inglês:

This paper integrates knowledge from physiology and psychophysics (i.e., visual perception) to propose a biological neural network model of cortical visual cell responses. We attempt to provide a model of how retinal and cortical cell interactions are able to detect static image luminance discontinuities -- such as at edges --, as well as moving luminance discontinuities -- i.e., motion stimuli. We address how important cortical cells known as simple cells combine retinal and thalamic signals to produce an effective contrast detection mechanism. An extension of the static model is then discussed in light of both psychophysical and physiological data on motion processing. The motion extension suggests a role for another important class of cortical cells known as complex cells. The static model is evaluated through a series of computer simulations that probe its capabilities with natural images, synthetic images (to assess noise tolerance), as well as images that allow us to compare the model's behavior with physiological results. The motion processing capabilities of the extended scheme are also evaluated through computer simulations. We suggest that this type of investigation can be used to attempt to advance our understanding of brain function, as well as devise powerful computational schemes that can be incorporated into artificial vision systems

Resumo em Inglês:

This paper introduces an associative memory model which associates n-tuples of patterns, employs continuous and limited pattern representation, performs both auto- and heteroassociative tasks, and has adaptable correlation matrices. This model called Temporal Multidirectional Associative Memory (TMAM) is an adaptation of the Multidirectional Associative Memory (MAM) which includes autoassociative links, real activation functions, and supervised learning rules. The experimental results suggest that the model presents fast learning, improves storage capacity of MAM, reproduces trained temporal sequences, interpolates states within a trained sequence, extrapolates states in both extremities of a given sequence, and accommodates sequences of different number of steps.

Resumo em Inglês:

This paper proposes five partially recurrent neural networks architectures to evaluate the different roles played by interlayer and intralayer feedback connections in planning a temporal sequence of states. The first model has only one-to-one feedback connections from the output towards the input layer. This topology is taken as the reference one. The other models have interlayer and/or intralayer all-to-all feedback connections added to them. All feedback connections, but the one-to-one feedback links, are trainable. The models yield a sequence which take four blocks from an initial to a goal state, when these states are presented to the network. The models showed good performance for planning in different levels of complexity. The results suggest that the models have poor generalization power.

Resumo em Inglês:

In the present paper, we propose a constrained information maximization method to control internal representations obtained in a course of learning. We focus upon hidden units and define information in hidden units acquired by learning. Internal representations are transformed by controlling this information. To control internal representations, a constraint is introduced in information maximization that total output from all the hidden units is a constant. By changing values of the constant, it is possible to generate many kinds of different internal representations, corresponding to the information content in hidden units. For example, we can obtain compact output patterns and specialized patterns of hidden units by changing the constant. We applied the constrained information maximization method to alphabet character recognition problems and a rule acquisition problem of an artificial language close to English. In the experiments, we were especially concerned with the generation of specialized hidden units, one of the typical example of the control of internal representations. Experimental results confirmed that we can control internal representations to produce specialized hidden units and to detect and extract main features of input patterns

Resumo em Inglês:

Bayesian techniques have been developed over many years in a range of different fields, but have only recently been applied to the problem of learning in neural networks. As well as providing a consistent framework for statistical pattern recognition, the Bayesian approach offers a number of practical advantages including a solution to the problem of over-fitting. This article provides an introductory overview of the application of Bayesian methods to neural networks. It assumes the reader is familiar with standard feed-forward network models and how to train them using conventional techniques