Syllabus

Foundations of Biological Neural Networks and Artificial Neural Networks (Learning, Generalization, Memory, Abstraction, Applications), McCulloch-Pitts Model, Historical Developments.ANN Architectures, Learning Strategy (Supervised, Unsupervised, Reinforcement), Applications: Function Approximation, Prediction, Optimization. Associative Memories: Matrix memories, Bidirectional Associative Memory, Hopfield Neural Network. Neural Architectures with Unsupervised Learning: Competitive learning, Principal Component Analysis Networks (PCA), Kohonen’s Self-Organizing Maps, Linear Vector Quantization, Adaptive Resonance Theory (ART) Networks, Independent Component Analysis Networks (ICA).