New trends in neural computation : International Workshop on Artificial Neural Networks, IWANN '93, Sitges, Spain, June 9-11, 1993 : proceedings

Neural computation arises from the capacity of nervous tissue to process information and accumulate knowledge in an intelligent manner. Conventional computational machines have encountered enormous difficulties in duplicatingsuch functionalities. This has given rise to the development of Artificial Neural Networks where computation is distributed over a great number of local processing elements with a high degree of connectivityand in which external programming is replaced with supervised and unsupervised learning. The papers presented in this volume are carefully reviewed versions of the talks delivered at the International Workshop on Artificial Neural Networks (IWANN '93) organized by the Universities of Catalonia and the Spanish Open University at Madrid and held at Barcelona, Spain, in June 1993. The 111 papers are organized in seven sections: biological perspectives, mathematical models, learning, self-organizing networks, neural software, hardware implementation, and applications (in five subsections: signal processing and pattern recognition, communications, artificial vision, control and robotics, and other applications). Biophysics of neural computation....Pages 1-11 Integrated learning in rana computatrix....Pages 12-19 A model for centering visual stimuli through adaptive value learning....Pages 20-23 A model for the development of neurons selective to visual stimulus size....Pages 24-29 An invariant representation mechanism after presynaptic inhibition....Pages 30-36 The pancreatic B-cell as a voltage-controlled oscillator....Pages 37-42 Approximation of the solution of the dendritic cable equation by a small series of coupled differential equations....Pages 43-48 A neural network model inspired in global appreciations about the thalamic reticular nucleus and cerebral cortex connectivity....Pages 49-54 Towards more realistic self contained models of neurons: High-order, recurrence and local learning....Pages 55-62 McCulloch's neurons revisited....Pages 63-67 Biologically motivated approach to face recognition....Pages 68-77 Learning by reinforcement: A psychobiological model....Pages 78-83 A neural state machine for iconic language representation....Pages 84-89 Variable binding using serial order in recurrent neural networks....Pages 90-95 Region of influence (ROI) networks. Model and implementation....Pages 96-101 A node splitting algorithm that reduces the number of connections in a Hamming distance classifying network....Pages 102-107 A high order neural model....Pages 108-113 Higher-order networks for the optimization of block designs....Pages 114-118 Neural Bayesian classifier....Pages 119-124 Constructive methods for a new classifier based on a radial-basis-function neural network accelerated by a tree....Pages 125-130 Practical realization of a radial basis function network for handwritten digit recognition....Pages 131-136 Design of fully and partially connected random neural networks for pattern completion....Pages 137-142 Representation and recognition of regular grammars by means of second-order recurrent neural networks....Pages 143-148 Connectionist models for syllabic recognition in the time domain....Pages 149-154 Sparsely interconnected artificial neural networks for associative memories....Pages 155-160 Dynamic analysis of networks of neural oscillators....Pages 161-166 Optimised attractor neural networks with external inputs....Pages 167-172 Non-orthogonal bases and metric tensors: An application to artificial neural networks....Pages 173-178 Genetic synthesis of discrete-time recurrent neural network....Pages 179-184 Optimization of a competitive learning neural network by genetic algorithms....Pages 185-192 Adaptive models in neural networks....Pages 193-197 Self-organizing grammar induction using a neural network model....Pages 198-203 The role of forgetting in efficient learning strategies for self-organising discriminator-based systems....Pages 204-209 Simulation of stochastic regular grammars through simple recurrent networks....Pages 210-215 Local stochastic competition and vector quantization....Pages 216-222 MHC — An evolutive connectionist model for hybrid training....Pages 223-229 Fast-convergence learning algorithms for multi-level and binary neurons and solution of some image processing problems....Pages 230-236 Invariant object recognition using fahlman and Lebiere's learning algorithm....Pages 237-242 Realization of subjective correspondence in artificial neural network trained by Fahlman and Lebiere's learning algorithm....Pages 243-248 Bimodal distribution removal....Pages 249-254 A simplified ARTMAP architecture for real-time learning....Pages 255-260 B-Learning: A reinforcement learning algorithm, comparison with dynamic programming....Pages 261-266 Increased complexity training....Pages 267-271 Optimized learning for improving the evolution of piecewise linear separation incremental algorithms....Pages 272-277 A method of pruning layered feed-forward neural networks....Pages 278-283 Tests of different regularization terms in small networks....Pages 284-290 On the distribution of feature space in Self-Organising mapping and convergence accelerating by a Kalman algorithm....Pages 291-296 A learning algorithm to obtain self-organizing maps using fixed neighbourhood Kohonen networks....Pages 297-304 Analysing a contingency table with Kohonen maps: A factorial correspondence analysis....Pages 305-311 Dynamics of self-organized feature mapping....Pages 312-315 Comparative study of self-organizing neural networks....Pages 316-321 GANNet: A genetic algorithm for optimizing topology and weights in neural network design....Pages 322-327 Vector quantization and projection neural network....Pages 328-333 Constructive design of LVQ and DSM classifiers....Pages 334-339 Linear vector classification: An improvement on LVQ algorithms to create classes of patterns....Pages 340-345 Non-greedy adaptive vector quantizers....Pages 346-350 Hybrid programming environments....Pages 351-357 Automatic generation of C++ code for neural network simulation....Pages 358-363 Urano: An object-oriented artificial neural network simulation tool....Pages 364-369 Realistic simulation tool for early visual processing including space, time and colour data....Pages 370-375 Language supported storage and reuse of persistent neural network objects....Pages 376-381 Flexible operating environment for matrix based neurocomputers....Pages 382-387 A parallel implementation of kohonen's self-organizing maps on the smart neurocomputer....Pages 388-393 Simulation of neural networks in a distributed computing environment using Neurograph....Pages 394-398 Full automatic ann design: A genetic approach....Pages 399-404 Hardware implementations of artificial neural networks....Pages 405-419 A neural network chip using CPWM modulation....Pages 420-425 Hardware implementation of a neural network for high energy physics application....Pages 426-431 MapA: An array processor architecture for neural networks....Pages 432-440 Limitation of connectionism in MLP....Pages 441-447 High level synthesis of neural network chips....Pages 448-453 Neural network simulations on massively parallel computers: Applications in chemical physics....Pages 454-458 A model based approach to the performance analysis of multi-layer networks realised in linear systolic arrays....Pages 459-464 The temporal noisy-leaky integrator neuron with additional inhibitory inputs....Pages 465-470 Architectures for self-learning neural network modules....Pages 471-475 The generic neuron architectural framework for the automatic generation of ASICs....Pages 476-481 A risc architecture to support neural net simulation....Pages 482-487 Hardware design for self organizing feature maps with binary input vectors....Pages 488-493 The Kolmogorov signal processor....Pages 494-512 Projectivity invariant pattern recognition with high-order neural networks....Pages 513-518 Rejection of incorrect answers from a neural net classifier....Pages 519-524 Nonlinear time series modeling by competitive segmentation of state space....Pages 525-530 Identification and prediction of non-linear models with recurrent neural network....Pages 531-535 Use of unsupervised neural networks for classification of blood pressure time series....Pages 536-541 Application of artificial neural networks to chest image classification....Pages 542-549 Combination of self-organizing maps and multilayer perceptrons for speaker independent isolated word recognition....Pages 550-555 An industrial application of neural networks to natural textures classification....Pages 556-562 Use of a layered neural nets as a display method for n-dimensional distributions....Pages 563-568 MLP modular versus yprel classifiers....Pages 569-574 How many hidden neurons are needed to recognize a symmetrical pattern ?....Pages 575-582 Hopfield neural network for routing....Pages 583-592 Neural network routing controller for communication parallel multistage interconnection networks....Pages 593-598 Adaptive routing using cellular automata....Pages 599-604 Optimal blind equalization of Gaussian channels....Pages 605-610 Noise prediction in urban traffic by a neural approach....Pages 611-619 A connectionist approach to the correspondence problem in computer vision....Pages 620-625 Self-organizing feature maps for image segmentation....Pages 626-631 Recognition of fractal images using a neural network....Pages 632-637 Feed forward network for vehicle license character recognition....Pages 638-644 Interpretation of optical flow through complex neural network....Pages 645-650 CT image segmentation by self-organizing learning....Pages 651-656 Texture image segmentation using a modified Hopfield network....Pages 657-663 Image compression with self-organizing networks....Pages 664-669 Neural networks as direct adaptive controllers....Pages 670-675 A neural adaptive controller for a turbofan exhaust nozzle....Pages 676-681 Feed-forward neural networks for bioreactor control....Pages 682-687 Learning networks for process identification and associative action....Pages 688-693 On-line performance enhancement of a behavioral neural network controller....Pages 694-701 An architecture for implementing control and signal processing neural networks....Pages 702-707 Planlite: Adaptive planning using weightless systems....Pages 708-713 Stock prices and volume in an artificial adaptive stock market....Pages 714-719 Application of the Fuzzy ARTMAP neural network architecture to bank failure predictions....Pages 720-725 Combination of neural network and statistical methods for sensory evalution of biological products: On-line beauty selection of flowers....Pages 726-731 An adaptive information retrieval system based on Neural Networks....Pages 732-737 Software pattern EEG recognition after a wavelet transform by a neural network....Pages 738-743 "Neural computation arises from the capacity of nervous tissue to process information and accumulate knowledge in an intelligent manner. Conventional computational machines have encountered enormous difficulties in duplicatingsuch functionalities. This has given rise to the development of Artificial Neural Networks where computation is distributed over a great number of local processing elements with a high degree of connectivityand in which external programming is replaced with supervised and unsupervised learning. The papers presented in this volume are carefully reviewed versions of the talks delivered at the International Workshop on Artificial Neural Networks (IWANN '93) organized by the Universities of Catalonia and the Spanish Open University at Madrid and held at Barcelona, Spain, in June 1993. The 111 papers are organized in seven sections: biological perspectives, mathematical models, learning, self-organizing networks, neural software, hardware implementation, and applications (in five subsections: signal processing and pattern recognition, communications, artificial vision, control and robotics, and other applications).'--PUBLISHER'S WEBSITE