Neural computing
I Jagielska
4 points * 2 hours per week * First semester (Clayton) * Second semester (Caulfield) * Prerequisites: Any minor sequence in computing, 2 units of maths
This subject provides students with a broad understanding of neural computing also known as neural networks. There will be a strong emphasis on application of neural networks in business and industry. In particular the following topics will be covered: the history, architecture and biological motivations; learning in neural networks - supervised vs unsupervised learning; the perceptron and its limitations, the multilayer perceptron; backpropagation, Kohonen self-organising map, counterpropagation, Hopfield network, bidirectional associative memories (BAM) network; fuzzy logic, neuro-fuzzy systems; neural networks implementations; applications of neural networks - neural network expert systems, neural networks and decision support tools, engineering applications; development of neural network applications using interactive environments, data preprocessing, building heuristic and techniques, training, testing, evaluating neural network performance.
Assessment
Examination: 2 hours
Prescribed texts
Beale R and Jackson T Neural computing: An introduction Adam Higler, 1990
Jagielska I Neural computing Monash U, 1993