Eight neural net and conventional pattern classifiers (Bayesianunimodal Gaussian,k-nearest neighbor, standard back-propagation, adaptive-stepsize back-propagation, hypersphere, feature-map, learning vectorquantizer, and binary decision tree) were implemented on a serial computer and compared using two speech recognition and two artificial tasks. Error rates were statistically equivalent on almost all tasks, but classifiers differed by orders of magnitude in memory requirements, training time, classification time, and ease of adaptivity. Nearest-neighbor classifiers trained rapidly but required themost memory. Tree classifiers provided rapid classification but were complex to adapt. Back-propagation classifiers typically requiredlong training times and had intermediate memory requirements. These results suggest that classifier selection should often depend more heavily on practical considerations concerning memory and computation resources, and restrictions on training and classification times than on error rate.

Spiking neurons which integrate to threshold and fire were used to study the transmission of frequency modulated (FM) signals through layered networks. Firing correlations between cells in the input layer were found to modulate the transmission of FM signals undercertain dynamical conditions. A tonic level of activity was maintained by providing each cell with a source of Poissondistributed synapticinput. When the average membrane depolarization produced by the synaptic input was sufficiently below threshold, the firing correlations between cells in the input layer could greatly amplify the signal present in subsequent layers. When the depolarization was sufficiently close to threshold, however, the firing synchrony between cells in the initial layers could no longer effect the propagation of FM signals. In this latter case, integrateand-fire neuronscould be effectively modeled by simpler analog elements governed by a linear input-output relation.

We describe a model that can recognize two-dimensional shapes in an unsegmented image, independent of their orientation, position, and scale. The model, called TRAFFIC, efficiently represents the structural relation between an object and each of its component features by encoding the fixed viewpoint-invariant transformation from the feature's reference frame to the object's in the weights of a connectionist network. Using a hierarchy of such transformations, with increasing complexity of features at each successive layer, the network can recognize multiple objects in parallel. An implementation ofTRAFFIC is described, along with experimental results demonstrating the network's ability to recognize constellations of stars in a viewpoint-invariant manner. 1 INTRODUCTION A key goal of machine vision is to recognize familiar objects in an unsegmented image, independent of their orientation, position, and scale. Massively parallel models have long been used for lower-level vision tasks, such as primitive feature extraction and stereo depth.

Previous attempts at using these visual speech signals to improve automatic speech recognition systems havecombined the acoustic and visual speech information at a symbolic level using heuristic rules. In this paper, we demonstrate an alternative approach to fusing the visual and acoustic speech information by training feedforward neural networks to map the visual signal onto the corresponding short-term spectral amplitude envelope (STSAE) of the acoustic signal. This information can be directly combined with the degraded acoustic STSAE. Significant improvementsare demonstrated in vowel recognition from noise-degraded acoustic signals. These results are compared to the performance of humans, as well as other pattern matching and estimation algorithms. 1 INTRODUCTION Current automatic speech recognition systems rely almost exclusively on the acoustic speechsignal, and as a consequence, these systems often perform poorly in noisy Combining Visual and Acoustic Speech Signals 233 environments.

In this paper, we present a novel implementation of the widely used Back-propagation neural net learning algorithm on the Connection Machine CM-2 - a general purpose, massively parallel computer with a hypercube topology. This implementation runs at about 180 million interconnections per second (IPS) on a 64K processor CM-2. The main interprocessor communication operation used is 2D nearest neighbor communication. The techniques developed here can be easily extended to implement other algorithms for layered neural nets on the CM-2, or on other massively parallel computers which have 2D or higher degree connections among their processors. 1 Introduction High-speed simulation of large artificial neural nets has become an important tool for solving real world problems and for studying the dynamic behavior of large populations of interconnected processing elements [3, 2]. This work is intended to provide such a simulation tool for a widely used neural net learning algorithm - the Back-propagation (BP) algorithm.[7] The hardware we have used is the Connection Machine CM-2.2

We have constructed a two axis camera positioning system which is roughly analogous to a single human eye. This Artificial-Eye (Aeye) combinesthe signals generated by two rate gyroscopes with motion information extracted from visual analysis to stabilize its camera. This stabilization process is similar to the vestibulo-ocular response (VOR); like the VOR, A-eye learns a system model that can be incrementally modified to adapt to changes in its structure, performance and environment. A-eye is an example of a robust sensory systemthat performs computations that can be of significant use to the designers of mobile robots. 1 Introduction We have constructed an "artificial eye" (A-eye), an autonomous robot that incorporates atwo axis camera positioning system (figure 1). Like a the human oculomotor system, A-eye can estimate the rotation rate of its body with a gyroscope and estimate therotation rate of its "eye" by measuring image slip

The properties of a cluster of multiple back-propagation (BP) networks are examined and compared to the performance of a single BP network. Theunderlying idea is that a synergistic effect within the cluster improves the perfonnance and fault tolerance. Five networks were initially trainedto perfonn the same input-output mapping. Following training, a cluster was created by computing an average of the outputs generated by the individual networks. The output of the cluster can be used as the desired output during training by feeding it back to the individual networks.In comparison to a single BP network, a cluster of multiple BP's generalization and significant fault tolerance. It appear that cluster advantage follows from simple maxim "you can fool some of the single BP's in a cluster all of the time but you cannot fool all of them all of the time" {Lincoln} 1 INTRODUCTION Shortcomings of back-propagation (BP) in supervised learning has been well documented inthe past {Soulie, 1987; Bernasconi, 1987}. Often, a network of a finite size does not learn a particular mapping completely or it generalizes poorly.

ABSTRACT The CHAC storage scheme has been used as a basis for a software implementation of an associative .emory A major disadvantage of this CHAC-concept is that the degree of local generalization (area of interpolation) isfixed. This paper deals with an algorithm for self-organizing variable generalization for the AKS, based on ideas of T. Kohonen. 1 INTRODUCTION For several years research at the Department of Control Theory andRobotics at the Technical University of Darmstadt has been concerned with the design of a learning real-time control loop with neuron-like associative memories (LERNAS) A Self-organizing Associative Memory System for Control Applications 333 for the control of unknown, nonlinear processes (Ersue, Tolle, 1988). This control concept uses an associative memory systemAHS, based on the cerebellar cortex model CHAC by Albus (Albus, 1972), for the storage of a predictive nonlinear processmodel and an appropriate nonlinear control strategy (Fig.1). Figure 1: The learning control loop LERNAS One problem for adjusting the control loop to a process is, however, to find a suitable set of parameters for the associative memory.The parameters in question determine the degree of generalization within the memory and therefore have a direct influence on the number of training steps required tolearn the process behaviour. For a good performance of the control loop it· is desirable to have a very small generalization around a given setpoint but to have a large generalization elsewhere. Actually, the amount of collected datais small during the transition phase between two 334 Hormel setpointsbut is large during setpoint control.

How good are the reconstructions?

Pentti Kanerva Research Institute for Advanced Computer Science Mail Stop 230-5, NASA Ames Research Center Moffett Field, California 94035 ABSTRACT Contour maps provide a general method for recognizing two-dimensional shapes. All but blank images give rise to such maps, and people are good at recognizing objects and shapes from them. The maps are encoded easily in long feature vectors that are suitable for recognition by an associative memory. These properties of contour maps suggest a role for them in early visual perception. The prevalence of direction-sensitive neurons in the visual cortex of mammals supports this view.