Kc. Tsui et al., THE ROLES OF NEURAL AND EVOLUTIONARY COMPUTING IN INTELLIGENT SOFTWARE SYSTEMS, British Telecom technology journal, 14(4), 1996, pp. 46-54
This paper describes two computing paradigms known as neural computing
and evolutionary computing, and their potential contribution to build
ing intelligent software systems. The paper begins by giving a brief i
ntroduction to the origins of each paradigm. Then two sections introdu
ce the basic principles, and identified, the role of each paradigm in
intelligent system design. Each section ends with a number of applicat
ions that have been or are being investigated. These include connectio
n admission control, modem communication, adaptive model-based control
, face and handwriting recognition, frequency assignment, help-desk sc
heduling, financial time-series prediction, face recognition and evolv
ing agent behaviour. ii section introduces the idea of using communica
tions theory to design neural networks and the paper concludes with th
e authors' views on the future of neural and evolutionary computing fo
r intelligent software systems.