String matching artificial neural networks.

Three artificial neural networks (ANNs) are proposed for solving a variety of on- and off-line string matching problems. The ANN structure employed as the building block of these ANNs is derived from the harmony theory (HT) ANN, whereby the resulting string matching ANNs are characterized by fast match-mismatch decisions, low computational complexity, and activation values of the ANN output nodes that can be used as indicators of substitution, insertion (addition) and deletion spelling errors.     

Modular neural networks: a survey.

Modular Neural Networks (MNNs) is a rapidly growing field in artificial Neural Networks (NNs) research. This paper surveys the different motivations for creating MNNs: biological, psychological, hardware, and computational. Then, the general stages of MNN design are outlined and surveyed as well, viz., task decomposition techniques, learning schemes and multi-module decision-making strategies. Advantages and disadvantages of the surveyed methods are pointed out, and an assessment with respect to practical potential is provided. Finally, some general recommendations for future designs are presented.     

The extraction of neural strategies from the surface EMG.

This brief review examines some of the methods used to infer central control strategies from surface electromyogram (EMG) recordings. Among the many uses of the surface EMG in studying the neural control of movement, the review critically evaluates only some of the applications. The focus is on the relations between global features of the surface EMG and the underlying physiological processes. Because direct measurements of motor unit activation are not available and many factors can influence the signal, these relations are frequently misinterpreted. These errors are compounded by the counterintuitive effects that some system parameters can have on the EMG signal. The phenomenon of crosstalk is used as an example of these problems. The review describes the limitations of techniques used to infer the level of muscle activation, the type of motor unit recruited, the upper limit of motor unit recruitment, the average discharge rate, and the degree of synchronization between motor units. Although the global surface EMG is a useful measure of muscle activation and assessment, there are limits to the information that can be extracted from this signal.     

Cephalopod neural networks

Cephalopods have arguably the largest and most complex nervous systems amongst the invertebrates; but despite the squid giant axon being one of the best studied nerve cells in neuroscience, and the availability of superb information on the morphology of some cephalopod brains, there is surprisingly little known about the operation of the neural networks that underlie the sophisticated range of behaviour these animals display. This review focuses on a few of the best studied neural networks: the giant fiber system, the chromatophore system, the statocyst system, the visual system and the learning and memory system, with a view to summarizing our current knowledge and stimulating new studies, particularly on the activities of identified central neurons, to provide a more complete understanding of networks within the cephalopod nervous system.     

Bayesian neural networks

A neural network that uses the basic Hebbian learning rule and the Bayesian combination function is defined. Analogously to Hopfield's neural network, the convergence for the Bayesian neural network that asynchronously updates its neurons' states is proved. The performance of the Bayesian neural network in four medical domains is compared with various classification methods. The Bayesian neural network uses more sophisticated combination function than Hopfield's neural network and uses more economically the available information. The naive Bayesian classifier typically outperforms the basic Bayesian neural network since iterations in network make too many mistakes. By restricting the number of iterations and increasing the number of fixed points the network performs better than the naive Bayesian classifier. The Bayesian neural network is designed to learn very quickly and incrementally.     

Feeding neural networks in the mollusc Aplysia

Aplysia feeding is striking in that it is executed with a great deal of plasticity. At least in part, this flexibility is a result of the organization of the feeding neural network. To illustrate this, we primarily discuss motor programs triggered via stimulation of the command-like cerebral-buccal interneuron 2 (CBI-2). CBI-2 is interesting in that it can generate motor programs that serve opposing functions, i.e., programs can be ingestive or egestive. When programs are egestive, radula-closing motor neurons are activated during the protraction phase of the motor program. When programs are ingestive, radula-closing motor neurons are activated during retraction. When motor programs change in nature, activity in the radula-closing circuitry is altered. Thus, CBI-2 stimulation stereotypically activates the protraction and retraction circuitry, with protraction being generated first, and retraction immediately thereafter. In contrast, radula-closing motor neurons can be activated during either protraction or retraction. Which will occur is determined by whether other cerebral and buccal neurons are recruited, e.g. radula-closing motor neurons tend to be activated during retraction if a second CBI, CBI-3, is recruited. Fundamentally different motor programs are, therefore, generated because CBI-2 activates some interneurons in a stereotypic manner and other interneurons in a variable manner.     

Oscillatory neural networks in the rabbit hippocampus

A model is described to account for damped oscillatory activity of two interacting neural populations, pyramidal cells and interneurons. This network in the hippocampus is treated as a lumped system with tine delays between elements. The physiological mechanism underlying the oscillatory activity appears to involve neural population interaction and cannot be described in terms of a network composed of but two neurons, a single pyramidal cell and a single interneuron. An unusual aspect of the model is the explicit incorporation of an ongoing background input to raise the mean level of activity of the pyramidal cell population. This model has evolved from a series of studies previously performed on cats. To test the model experiments were performed on rabbits. The data showing oscillatory activity following fornix stimulation in the rabbit indicate that the model can be applied not only to the cat but also to the rabbit. In additions, for commissural stimulation oscillatory potentials of neural populations and individual pyramidal cells were evoked as predicted by the model.     

Hypnosis modelling in neural networks

In the framework of the neural network theory effects similar to hypnotic displays are constructed. They are based on the associative paradigm involving non-linear interaction of excitatory and inhibitory channels with synaptic memory. The non-linearity of long-term memorizing processes may cause effects exhibited by blind spots, which are interpreted as the first stage of hypnosis. More complicated phenomena are discussed in terms of a two-layer network.     

Dynamic connections in neural networks

Massively parallel (neural-like) networks are receiving increasing attention as a mechanism for expressing information processing models. By exploiting powerful primitive units and stability-preserving construction rules, various workers have been able to construct and test quite complex models, particularly in vision research. But all of the detailed technical work was concerned with the structure and behavior offixed networks. The purpose of this paper is to extend the methodology to cover several aspects of change and memory.     

Asymptotic hyperstability of a class of neural networks.

This paper is concerned with the asymptotic hyperstability of recurrent neural networks. We derive based on the stability results necessary and sufficient conditions for the network parameters. The results we achieve are more general than those based on Lyapunov methods, since they provide milder constraints on the connection weights than the conventional results and do not suppose symmetry of the weights.     

Motif-based protein sequence classification using neural networks.

We present a system for multi-class protein classification based on neural networks. The basic issue concerning the construction of neural network systems for protein classification is the sequence encoding scheme that must be used in order to feed the neural network. To deal with this problem we propose a method that maps a protein sequence into a numerical feature space using the matching scores of the sequence to groups of conserved patterns (called motifs) into protein families. We consider two alternative ways for identifying the motifs to be used for feature generation and provide a comparative evaluation of the two schemes. We also evaluate the impact of the incorporation of background features (2-grams) on the performance of the neural system. Experimental results on real datasets indicate that the proposed method is highly efficient and is superior to other well-known methods for protein classification.     

Sleep classification in infants based on artificial neural networks.

The study reports on the possibility of classifying sleep stages in infants using an artificial neural network. The polygraphic data from 4 babies aged 6 weeks, 6 months and 1 year recorded over 8 hours were available for classification. From each baby 22 signals were recorded, digitized and stored on an optical disc. Subsets of these signals and additional calculated parameters were used to obtain data vectors, each of which represents an interval of 30 sec. For classification, two types of neural networks were used, a Multilayer Perceptron and a Learning Vector Quantizer. The teaching input for both networks was provided by a human expert. For the 6 sleep classes in babies aged 6 months, a 65% to 80% rate of correct classification (4 babies) was obtained for the testing data not previously seen.     

Clustering with neural networks

Partitioning a set ofN patterns in ad-dimensional metric space intoK clusters — in a way that those in a given cluster are more similar to each other than the rest — is a problem of interest in many fields, such as, image analysis, taxonomy, astrophysics, etc. As there are approximatelyK ^N/K! possible ways of partitioning the patterns amongK clusters, finding the best solution is beyond exhaustive search whenN is large. We show that this problem, in spite of its exponential complexity, can be formulated as an optimization problem for which very good, but not necessarily optimal, solutions can be found by using a Hopfield model of neural networks. To obtain a very good solution, the network must start from many randomly selected initial states. The network is simulated on the MPP, a 128 × 128 SIMD array machine, where we use the massive parallelism not only in solving the differential equations that govern the evolution of the network, but also in starting the network from many initial states at once thus obtaining many solutions in one run. We achieve speedups of two to three orders of magnitude over serial implementations and the promise through Analog VLSI implementations of further speedups of three to six orders of magnitude.Supported by a National Research Council-NASA Research Associatship