Neural information processing : research and development

This monograph presents a careful collection of recent research and developments in the field of neural information processing. This includes investigations in the functioning and engineering of biological neural networks and applications of artificial neural networks for solving real-world problems. The book is organized in three parts, architectures, learning algorithms and applications, with a variety of different examples and case studies from different fields such as the visual system, object detection, financial time series prediction, the auditory cortex, and robot manipulator control. Front Matter....Pages I-IX Scale Independence in the Visual System....Pages 1-18 Dynamic Neuronal Information Processing of Vowel Sounds in Auditory Cortex....Pages 19-38 Convolutional Spiking Neural Network for Robust Object Detection with Population Code Using Structured Pulse Packets....Pages 39-55 Networks constructed of neuroid elements capable of temporal summation of signals....Pages 56-76 Predictive synchrony organized by spike-based Hebbian learning with time-representing synfire activities....Pages 77-93 Improving Chow-Liu Tree Performance by Mining Association Rules....Pages 94-112 A Reconstructed Missing Data-Finite Impulse Response Selective Ensemble (RMD-FSE) Network....Pages 113-127 Higher Order Multidirectional Associative Memory with Decreasing Energy Function....Pages 128-149 Fast Indexing of Codebook Vectors Using Dynamic Binary Search Trees With Fat Decision Hyperplanes....Pages 150-166 On Some External Characteristics of Brain-like Learning and Some Logical Flaws of Connectionism....Pages 167-179 Superlinear Learning Algorithm Design....Pages 180-210 Extension of Binary Neural Networks for Multi-class Output and Finite Automata....Pages 211-237 A Memory-Based Reinforcement Learning Algorithm to Prevent Unlearning in Neural Networks....Pages 238-255 Structural Optimization of Neural Networks by Genetic Algorithm with Degeneration (GA d )....Pages 256-277 Adaptive Training for Combining Classifier Ensembles....Pages 278-293 Combination Strategies for Finding Optimal Neural Network Architecture and Weights....Pages 294-319 Biologically inspired recognition system for car detection from real-time video streams....Pages 320-333 Financial Time Series Prediction Using Non-fixed and Asymmetrical Margin Setting with Momentum in Support Vector Regression....Pages 334-350 A Method for Applying Neural Networks to Control of Nonlinear Systems....Pages 351-369 Robot Manipulator Control via Recurrent Neural Networks....Pages 370-386 Gesture Recognition Based on SOM Using Multiple Sensors....Pages 387-404 Enhanced phrase-based document clustering using Self-Organizing Map (SOM) architectures....Pages 405-424 Discovering gene regulatory networks from gene expression data with the use of evolving connectionist systems....Pages 425-436 Experimental Analysis of Knowledge Based Multiagent Credit Assignment....Pages 437-459 Implementation of Visual Tracking System using Artificial Retina Chip and Shape Memory Alloy Actuator....Pages 460-477 The field of neural information processing has two main objects: investigation into the functioning of biological neural networks and use of artificial neural networks to sol ve real world problems. Even before the reincarnation of the field of artificial neural networks in mid nineteen eighties, researchers have attempted to explore the engineering of human brain function. After the reincarnation, we have seen an emergence of a large number of neural network models and their successful applications to solve real world problems. This volume presents a collection of recent research and developments in the field of neural information processing. The book is organized in three Parts, i.e., (1) architectures, (2) learning algorithms, and (3) applications. Artificial neural networks consist of simple processing elements called neurons, which are connected by weights. The number of neurons and how they are connected to each other defines the architecture of a particular neural network. Part 1 of the book has nine chapters, demonstrating some of recent neural network architectures derived either to mimic aspects of human brain function or applied in some real world problems. Muresan provides a simple neural network model, based on spiking neurons that make use of shunting inhibition, which is capable of resisting small scale changes of stimulus. Hoshino and Zheng simulate a neural network of the auditory cortex to investigate neural basis for encoding and perception of vowel sounds.