DocumentCode
799977
Title
Hybrid connectionist systems in research and teaching
Author
Jain, L.C.
Author_Institution
Knowledge-Based Eng. Syst. Group, South Australia Univ., Adelaide, SA, Australia
Volume
10
Issue
3
fYear
1995
fDate
3/1/1995 12:00:00 AM
Firstpage
14
Lastpage
18
Abstract
There is a tremendous world-wide interest in the development of the theory and application of artificial intelligence (AI) and related techniques both in tertiary institutions and in industry. This paper presents a brief survey of overseas AI teaching programs together with a review of the teaching program in the University of South Australia. In addition, post-graduate projects undertaken by the Knowledge-Engineering Systems Group (KES), and sponsored by the Defence, Science and Technology Organisation (DSTO), are discussed. These involve expert systems, neural networks, fuzzy logic and genetic algorithms. It is shown by using a classical exclusive-OR problem that it is useful to use hybrid techniques which offer fast convergence in optimization problems. Although much of this work is still at an early stage, sufficient progress has been made to demonstrate the merit of using AI and related techniques to help create solutions to these problems
Keywords
artificial intelligence; educational technology; engineering education; expert systems; knowledge based systems; neural nets; research and development management; teaching; Knowledge-Engineering Systems Group; University of South Australia; artificial intelligence; convergence; exclusive-OR problem; expert systems; fuzzy logic; genetic algorithms; hybrid connectionist system; hybrid techniques; neural networks; optimization; overseas AI teaching; research; teaching; tertiary institutions; Application software; Artificial intelligence; Australia; Education; Expert systems; Fuzzy logic; Genetic algorithms; Knowledge engineering; Neural networks; Systems engineering and theory;
fLanguage
English
Journal_Title
Aerospace and Electronic Systems Magazine, IEEE
Publisher
ieee
ISSN
0885-8985
Type
jour
DOI
10.1109/62.391916
Filename
391916
Link To Document