Trends in Neural Computation

Nowadays neural computation has become an interdisciplinary field in its own right; researches have been conducted ranging from diverse disciplines, e.g. computational neuroscience and cognitive science, mathematics, physics, computer science, and other engineering disciplines. From different perspectives, neural computation provides an alternative methodology to understand brain functions and cognitive process and to solve challenging real-world problems effectively.

Trends in Neural Computation includes twenty chapters either contributed from leading experts or formed by extending well selected papers presented in the 2005 International Conference on Natural Computation. The edited book aims to reflect the latest progresses made in different areas of neural computation, including theoretical neural computation, biologically plausible neural modeling, computational cognitive science, artificial neural networks architectures and learning algorithms and their applications in real-world problems.

reflects the latest progresses made in different areas of neural computation provides an alternative methodology to understand brain functions and cognitive process and to solve challenging real-world problems effectively includes theoretical neural computation, biologically plausible neural modeling, computational cognitive science, artificial neural networks architectures and learning algorithms and their applications in real-world problems. Includes supplementary material: sn.pub/extras

Inhalt
Hyperbolic Function Networks for Pattern Classification.- Variable Selection for the Linear Support Vector Machine.- Selecting Data for Fast Support Vector Machines Training.- Universal Approach to Study Delayed Dynamical Systems.- A Hippocampus-Neocortex Model for Chaotic Association.- Latent Attractors: A General Paradigm for Context-Dependent Neural Computation.- Learning Mechanisms in Networks of Spiking Neurons.- GTSOM: Game Theoretic Self-organizing Maps.- How to Generate Different Neural Networks.- A Gradient-Based Forward Greedy Algorithm for Space Gaussian Process Regression.- An Evolved Recurrent Neural Network and Its Application.- A Min-Max Modular Network with Gaussian-Zero-Crossing Function.- Combining Competitive Learning Networks of Various Representations for Sequential Data Clustering.- Modular Neural Networks and Their Applications in Biometrics.- Performance Analysis of Dynamic Cell Structures.- Short Term Electric Load Forecasting: A Tutorial.- Performance Improvement for Formation-Keeping Control Using a Neural Network HJI Approach.- A Robust Blind Neural Equalizer Based on Higher-Order Cumulants.- The Artificial Neural Network Applied to Servo Control System.- Robot Localization Using Vision.