Integrated feature and parameter optimization for an evolving spiking neural network: Exploring heterogeneous probabilistic models

2009 ◽  
Vol 22 (5-6) ◽  
pp. 623-632 ◽  
Author(s):  
Stefan Schliebs ◽  
Michaël Defoin-Platel ◽  
Sue Worner ◽  
Nikola Kasabov
Keyword(s):  
Neural Network ◽  
Parameter Optimization ◽  
Probabilistic Models ◽  
Spiking Neural Network ◽  
Evolving Spiking Neural Network

A Biologically Inspired Evolving Spiking Neural Model with Rank-Order Population Coding and a Taste Recognition System Case Study

2011 ◽  
pp. 136-155 ◽  
Author(s):  
S. Soltic ◽  
N. Kasabov
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Rank Order ◽  
Neural Model ◽  
Recognition System ◽  
Population Coding ◽  
Spiking Neural Network ◽  
Biologically Inspired ◽  
Information Encoding ◽  
Evolving Spiking Neural Network

The human brain has an amazing ability to recognize hundreds of thousands of different tastes. The question is: can we build artificial systems that can achieve this level of complexity? Such systems would be useful in biosecurity, the chemical and food industry, security, in home automation, etc. The purpose of this chapter is to explore how spiking neurons could be employed for building biologically plausible and efficient taste recognition systems. It presents an approach based on a novel spiking neural network model, the evolving spiking neural network with population coding (ESNN-PC), which is characterized by: (i) adaptive learning, (ii) knowledge discovery and (iii) accurate classification. ESNN-PC is used on a benchmark taste problem where the effectiveness of the information encoding, the quality of extracted rules and the model’s adaptive properties are explored. Finally, applications of ESNN-PC in recognition of the increasing interest in robotics and pervasive computing are suggested.

Sign in / Sign up

Export Citation Format

Share Document