ABSTRACT
Neurocomputing is an emergent technology concerned with information processing systems that autonomously develop operational capabilities in adaptive response to an information environment. The principal information processing structures of interest in neurocomputing are computational neural networks, although other classes of adaptive information systems are also considered, such as genetic learning systems, fuzzy learning systems, and simulated annealing systems. Several features distinguish this approach to information processing from algorithmic and rule-based information systems (Fischer, 1994, 1995):
This relatively new approach to information processing offers great potential for tackling difficult problems, especially in those areas of pattern recognition and exploratory data analysis for which the algorithms and rules are not known, or where they might be known but the software to implement them would be too expensive or too time-consuming to develop. Indeed, with a neurocomputing solution, the only bespoke software that would need to be developed will in most instances be for relatively straightforward operations such as data preprocessing, data file input, data post-processing and data file output. Computer aided software engineering (CASE) tools could be used to build the appropriate routine software modules (Hecht-Nielsen, 1990).
