AIMS This course introduces the fundamentals of neural networks, basic philosophy of neural network architectures and its relation to practical problems such as image and speech processing. It introduces the association techniques, classification and clustering. It illustrates the concepts of building, training and testing a neural network. LEARNING OUTCOMES Knowledge On completion of this module, the successful student will be able to: • Appreciate the concept of Neural Network • Contrast human perception with electronic perception. • Compare the different types of Neural Networks. • Classify Neural Networks. Skills This module will call for the successful student to demonstrate: • Implement Neural Networks concepts to solve problems. • Use Neural Networks tools to design, train the network. • Build different Neural Networks applications such as OCR (Optical Character Recognition), forecasting … etc. SYLLABUS • Introduction. • Classification. • Simple Perception. • Adeline Network. • Unsupervised Learning Network. • Association & Auto association TEACHING/LEARNING STRATEGIES • Weekly lectures to introduce the basic concepts of the course subjects. • Weekly tutorials to discuss the solution of the weekly homework assignments. • Weekly computer laboratory to use readymade software to apply the concepts of Neural Networks to solving problems. • Class presentations the student will be assigned a specific subject to investigate in depth and make in class presentation. Assessment Scheme • Unseen Examinations 60 % • Coursework 40% Learning materials Elements of Artificial Neural Networks by Kishan Mehrotra, Chilukuri K. Mohan, and Sanjay Ranka, MIT Press, 1996