Understanding the response of neural nets to structural/functional damage is important fora variety of reasons, e.g., in assessing the performance of neural network hardware, and in gaining understanding of the mechanisms underlying neurological andpsychiatric disorders. Recently, there has been a growing interest in constructing neuralmodels to study how specific pathological neuroanatomical and neurophysiological changes can result in various clinical manifestations, and to investigate thefunctional organization of the symptoms that result from specific brain pathologies (reviewed in [1, 2]). In the area of associative memory models specifically, earlystudies found an increase in memory impairment with increasing lesion severity (in accordance with Lashley's classical'mass action' principle), and showed that slowly developing lesions have less pronounced effects than equivalent acute lesions [3]. Recently, it was shown that the gradual pattern of clinical deterioration manifested in the majority of Alzheimer's patients can be accounted for, and that different synaptic compensation rates can account for the observed variation in the severity and progression rate of this disease [4]. However, this past work is limited in that model elements have no spatial relationships to one another (all elements are conceptually equidistant).

MLP networks provided slightly better risk prediction than conventional logistic regression when used to predict the risk of death, stroke, and renal failure on 1257 patients who underwent coronaryartery bypass operations. Bootstrap sampling was required to compare approaches and regularization provided by early stopping was an important component of improved performance. A simplified approach to generating confidence intervals for MLP risk predictions using an auxiliary "confidence MLP" was also developed. The confidence MLP is trained to reproduce the confidence bounds that were generated during training by 50 MLP networks trained using bootstrap samples. Current research is validating these results usinglarger data sets, exploring approaches to detect outlier patients who are so different fromany training patient that accurate risk prediction is suspect, developing approaches toexplaining which input features are important for an individual patient, and determining why MLP networks provide improved performance.

A suggestive computational model for how such separate modules can be learned and combined is the mixture-of-experts neural network architecture (Jacobs et al., 1991).

Random errors and insufficiencies in databases limit the performance ofany classifier trained from and applied to the database. In this paper we propose a method to estimate the limiting performance ofclassifiers imposed by the database. We demonstrate this technique on the task of predicting failure in telecommunication paths. 1 Introduction Data collection for a classification or regression task is prone to random errors, e.g.

For many types of learners one can compute the statistically "optimal" wayto select data. We review how these techniques have been used with feedforward neural networks [MacKay, 1992; Cohn, 1994] . We then show how the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression areboth efficient and accurate.

Most of the recent emphasis in the neural network control field has no error feedback as the control input, which rises the lack of adaptation problem. The integrated architecture in this paper combines feed forward control and error feedback adaptive control using neural networks. The paper reveals the different internal functionality of these two kinds of neural network controllers for certain input styles, e.g., state feedback and error feedback. With error feedback, neural network controllers learn the slopes or the gains with respect to the error feedback, producing an error driven adaptive control systems. The results demonstrate that the two kinds of control scheme can be combined to realize their individual advantages. Testing with disturbances added to the plant shows good tracking and adaptation with the integrated neural control architecture.

We implement and study a computational model of Stevens' [19921 theory of the pathogenesis of schizophrenia. This theory hypothesizes thatthe onset of schizophrenia is associated with reactive synaptic regeneration occurring in brain regions receiving degenerating temporallobe projections. Concentrating on one such area, the frontal cortex, we model a frontal module as an associative memory neural network whose input synapses represent incoming temporal projections. We analyze how, in the face of weakened external input projections, compensatory strengthening of internal synaptic connections and increased noise levels can maintain memory capacities(which are generally preserved in schizophrenia). However, These compensatory changes adversely lead to spontaneous, biasedretrieval of stored memories, which corresponds to the occurrence of schizophrenic delusions and hallucinations without anyapparent external trigger, and for their tendency to concentrate onjust few central themes. Our results explain why these symptoms tend to wane as schizophrenia progresses, and why delayed therapeuticalintervention leads to a much slower response.

This paper is available with figures in colors as ftp: / / ftp .

This paper studies the problem of diffusion in Markovian models, such as hidden Markov models (HMMs) and how it makes very difficult the task of learning of long-term dependencies in sequences. Using results from Markov chain theory, we show that the problem of diffusion is reduced if the transition probabilities approach 0 or 1. Under this condition, standard HMMs have very limited modeling capabilities, but input/output HMMs can still perform interesting computations.

Many different discrete-time recurrent neural network architectures havebeen proposed. However, there has been virtually no effort to compare these arch:tectures experimentally. In this paper we review and categorize many of these architectures and compare how they perform on various classes of simple problems including grammatical inference and nonlinear system identification.