Neural networks are sets of interconnected artificial neurons that, very simplistically, imitate some of the logical functioning of the brain. Fuzzy logic emulates the reliable but approximate reasoning of humans, who, it is said, distinguish only six or seven different levels of any variable during decision making. Genetic algorithms and genetic programming are powerful evolutionary search methods that can search for structures as well as numerical parameters. Learning systems aim to emulate the human learning-by-experience mechanism so that a system can potentially learn to perform a task with increasing efficiency over time using an iterative algorithm. Intelligent machines and machine intelligence offer future prospects for creating systems with ever increasing autonomy and reasoning ability.

Chapter Contents:

• 17.1 Introduction
• 17.2 Artificial neural networks (ANN)
• 17.2.1 Motivation
• 17.2.2 A basic building block - the neuron
• 17.2.3 Simple properties of a neuron demonstrated in the two dimensional real plane
• 17.2.4 Multilayer networks
• 17.2.5 Neural network training
• 17.2.6 Neural network architectures to represent dynamic processes
• 17.2.7 Using neural net based self-organising maps for data-reduction and clustering
• 17.2.8 Upcoming rivals to neural networks? - support vector machines (SVMs) and adaptive logic networks (ALNs)
• 17.2.9 Neural nets - summary
• 17.3 Fuzzy set theory and fuzzy logic
• 17.3.1 Introduction and motivation
• 17.3.2 Some characteristics of fuzzy logic
• 17.3.3 References: early pioneering work
• 17.4 Genetic algorithms
• 17.4.1 Basic ideas
• 17.4.2 Artificial genetic algorithms
• 17.4.3 Genetic algorithms as design tools
• 17.4.4 GA summary
• 17.4.5 References
• 17.4.6 Rivals to GAs? Autonomous agents and swarms
• 17.5 Learning systems (systems that learn) with or without supervision
• 17.5.1 Basic ideas
• 17.5.2 Learning versus adaptivity
• 17.5.3 Structural characteristics of an abstract learning system
• 17.6 Intelligent systems
• 17.6.1 The properties that an intelligent system ought to possess
• 17.6.2 Selected references
• 17A The idea of a probing controller

Inspec keywords: genetic algorithms; brain; neural nets; learning systems; fuzzy logic

Other keywords: artificial neurons interconnection; brain; neural networks; genetic programming; logical functioning; learning systems; genetic algorithms; fuzzy logic; intelligent machines

Subjects: Neural nets (theory)