Syllabus

Neuron Model, Single-Input Neuron, Transfer Functions, Multiple-Input Neuron, Network Architectures: A Layer of Neurons, Multiple Layers of Neurons, Recurrent Networks, Learning Techniques.

Perceptron Learning: Theory and Examples; Learning Rules; Perceptron Architecture; Single-Neuron Perceptron; Multiple-Neuron Perceptron; Perceptron Learning Rule; Constructing Learning Rules; Unified Learning Rule; Training Multiple-Neuron Perceptron

Multilayer Perceptron: Back propagation algorithm, Covers theorem, Radial-basis function Networks, Support Vector Machines

Introduction to Deep learning, Convolutional Neural Networks, LeNet, ResNet, Deep auto-encoders, Deep generative models (GAN)

Introduction to Recursive Neural network (RNN), LSTM, Attention mechanism, Transformer

To design and development of neural networks and deep learning algorithms

To analyze the real time problem and find solution to the same using Neural Networks and Deep Learning techniques

To understand the fundamentals of neural networks.

To design and develop perceptron learning algorithms for pattern classification.

To develop learning algorithms for different neural networks.

To understand and develop different discriminative and generative deep learning models.

To understand and develop recurrent networks and attention mechanisms.

Martin T. Hagan, Howard B. Demuth, Mark H. Beale, , Neural Network Design, Thomson , 1996

Christopher M. Bishop, , Deep Learning: Foundations and Concepts, Springer , 2023

S. Haykin, Neural Networks and Learning Machines, Prentice Hall of India , 2010

lan Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press , 2016