A novel unsupervised neural network for dimensionality reduction which seeks directions emphasizing multimodality is presented, and its connection to exploratory projection pursuit methods is discussed. This leads to a new statistical insight to the synaptic modification equations governing learning in Bienenstock, Cooper, and Munro (BCM) neurons (1982). The importance of a dimensionality reduction principle based solely on distinguishing features, is demonstrated using a linguistically motivated phoneme recognition experiment, and compared with feature extraction using back-propagation network. 1 Introduction Due to the curse of dimensionality (Bellman, 1961) it is desirable to extract features from a high dimensional data space before attempting a classification. How to perform this feature extraction/dimensionality reduction is not that clear. A first simplification is to consider only features defined by linear (or semi-linear) projections of high dimensional data. This class of features is used in projection pursuit methods (see review in Huber, 1985). Even after this simplification, it is still difficult to characterize what interesting projections are, although it is easy to point at projections that are uninteresting. A statement that has recently been made precise by Diaconis and Freedman (1984) says that for most high-dimensional clouds, most low-dimensional projections are approximately normal. This finding suggests that the important information in the data is conveyed in those directions whose single dimensional projected distribution is far from Gaussian, especially at the center of the distribution.

Combining neuropharmacological experiments with computational modeling, we have shown that cholinergic modulation may enhance associative memory function in piriform (olfactory) cortex. We have shown that the acetylcholine analogue carbachol selectively suppresses synaptic transmission between cells within piriform cortex, while leaving input connections unaffected. When tested in a computational model of piriform cortex, this selective suppression, applied during learning, enhances associative memory performance.

This srudy has demonstrated how artificial neural networks (ANNs) can be used to characterize seismic sources using high-frequency regional seismic data. We have taken the novel approach of using ANNs as a research tool for obtaining seismic source information, specifically depth of focus for earthquakes and ripple-fire characteristics for economic blasts, rather than as just a feature classifier between earthquake and explosion populations. Overall, we have found that ANNs have potential applications to seismic event characterization and identification, beyond just as a feature classifier. In future studies, these techniques should be applied to actual data of regional seismic events recorded at the new regional seismic arrays. The results of this study indicates that an ANN should be evaluated as part of an operational seismic event identification system. 1 INTRODUCTION ANNs have usually been used as pattern matching algorithms, and recent studies have applied ANNs to standard classification between classes of earthquakes and explosions using wavefonn features (Dowla, et al, 1989), (Dysart and Pulli, 1990).

Feedback connections are required so that the teacher signal on the output neurons can modify weights during supervised learning. Relaxation methods are needed for learning static patterns with full-time feedback connections. Feedback network learning techniques have not achieved wide popularity because of the still greater computational efficiency of back-propagation. We show by simulation that relaxation networks of the kind we are implementing in VLSI are capable of learning large problems just like back-propagation networks. A microchip incorporates deterministic mean-field theory learning as well as stochastic Boltzmann learning. A multiple-chip electronic system implementing these networks will make high-speed parallel learning in them feasible in the future.

Barto, Sutton and Watkins [2] introduced a grid task as a didactic example of temporal difference planning and asynchronous dynamical pre gramming. This paper considers the effects of changing the coding of the input stimulus, and demonstrates that the self-supervised learning of a particular form of hidden unit representation improves performance.

Diagnosis of faults in complex, real-time control systems is a complicated task that has resisted solution by traditional methods. We have shown that neural networks can be successfully employed to diagnose faults in digitally controlled powertrain systems. This paper discusses the means we use to develop the appropriate databases for training and testing in order to select the optimum network architectures and to provide reasonable estimates of the classification accuracy of these networks on new samples of data.

Neural network simulations of the dragonfly flight neurocontrol system have been developed to understand how this insect uses complex, unsteady aerodynamics. The simulation networks account for the ganglionic spatial distribution of cells as well as the physiologic operating range and the stochastic cellular fIring history of each neuron. In addition the motor neuron firing patterns, "flight command sequences", were utilized. Simulation training was targeted against both the cellular and flight motor neuron firing patterns. The trained networks accurately resynthesized the intraganglionic cellular firing patterns. These in tum controlled the motor neuron fIring patterns that drive wing musculature during flight. Such networks provide both neurobiological analysis tools and fIrst generation controls for the use of "unsteady" aerodynamics.

We formulate the problem of optimizing the sampling of natural images using an array of linear filters. Optimization of information capacity is constrained by the noise levels of the individual channels and by a penalty for the construction of long-range interconnections in the array. At low signal-to-noise ratios the optimal filter characteristics correspond to bound states of a Schrodinger equation in which the signal spectrum plays the role of the potential. The resulting optimal filters are remarkably similar to those observed in the mammalian visual cortex and the retinal ganglion cells of lower vertebrates. The observed scale invariance of natural images plays an essential role in this construction.

Feature selective cells in the primary visual cortex of several species are organized in hierarchical topographic maps of stimulus features like "position in visual space", "orientation" and" ocular dominance". In order to understand and describe their spatial structure and their development, we investigate a self-organizing neural network model based on the feature map algorithm. The model explains map formation as a dimension-reducing mapping from a high-dimensional feature space onto a two-dimensional lattice, such that "similarity" between features (or feature combinations) is translated into "spatial proximity" between the corresponding feature selective cells. The model is able to reproduce several aspects of the spatial structure of cortical maps in the visual cortex. 1 Introduction Cortical maps are functionally defined structures of the cortex, which are characterized by an ordered spatial distribution of functionally specialized cells along the cortical surface. In the primary visual area(s) the response properties of these cells must be described by several independent features, and there is a strong tendency to map combinations of these features onto the cortical surface in a way that translates "similarity" into "spatial proximity" of the corresponding feature selective cells (see e.g.

Spoken input to computers, however, has yet to pass the threshold of practicality. Despite some recent successful demonstrations, current speech recognition systems typically fall far short of human capabilities of continuous speech recognition with essentially unrestricted vocabulary and speakers, under adverse acoustic environments.