Credit units

Pre-requisites: Fundamentals of neural network, basics of algorithms, probability and linear algebra.

Course Contents/Syllabus:

	Weightage (%)
Module I Introduction	20%
Descriptors/Topics Neural Networks, Single Layer And Multi-Layer Perceptions, Radial-Basis Function Networks, Bayesian Learning of Network Weight, Kohonen Self-Organizing Maps, Self-Learning In Neural Networks, Associative Memories, SVM for Binary Classification, Deep Neural Network, Convolutional Neural Network, Recurrent Neural Network, Attention Model
Module II Theory of Artificial Neural Networks and Recent Advances	25%
Descriptors/Topics Regularization Theory. Information-Theoretic Learning, Neurodynamics, Complex-Valued Neural Networks, The Logic Of Neural Cognition, Statistical Pattern Recognition, Algebraic Structure Of Feedforward Network, Speeding Up Backpropagation, Exploration Of A Natural Environment, Local Learning Rules And Sparse Coding In Neural Networks, Genetic Modeling, Hybrid Systems, Integration of Fuzzy Logic, Neural Networks And Genetic Algorithms, Non Traditional Optimization Techniques Like Ant Colony Optimization, Particle Swarm Optimization And Artificial

Immune Systems, Applications In Design And Manufacturing.