BUS5650 - Business applications of neural networks

Offered

Clayton Second semester 2007 (Day)

Synopsis

Solving practical business problems using commercially available neural network software. Focuses on business applications, with discussion of suitable neural network architectures and convergence issues. Students gain hands-on experience with commercial neural network software packages, and solve real business problems in labs and assignments. Topics include principles and mechanisms in neural networks; perceptions for marketing and business data classification/analysis; multilayer feedforward neural networks for time series, stock market prediction and written character recognition; convergence issues of neural networks, data mining methodologies and artificial intelligence in business.

Assessment

Examination (2 hours): 50%
Practical work (assignment): 30%
Mid-semester test: 20%
Students must pass the examination in order to pass the unit

Contact hours

One x 2hour lecture/week, one x 1hour laboratory/week

Prerequisites

Completion of 12 points of postgraduate level Faculty of Information Technology units

Prohibitions

BUS3650