Introduction to AI and Machine learning, Brief history and soft& hard computing (5 hrs)

Biological neuron, Artificial neural networks-classification, leaning laws, activation functions, Classification, regression, association and clustering. (7 hrs)

Perceptron model, multilayer perceptron, Hopfield model and other Association models, (7 hrs)

Clustering neural networks: Self organization, Adaptive resonance theory, Max net, Hybrid neural networks, (6 hrs)

Applications of neural networks: Hand written character recognition, robot kinematics, controllers and observers. (5hrs)
Artificial Intelligence, Expert system design, Natural Language understanding, Knowledge representation, Types of AI languages, Some case studies (6 hrs.)

To understand role of neural networks in machine learning

To study the modern AI tools and its applications including expert systems and NLP.

To learn the programming aspects of neural networks

To gain the concept of forward and inverse feedback controller designs using neural networks

To gain the differences in hard and soft computing methods

To understand the basic mathematics of artificial neural networks

To learn the classification, regression, clustering and association problems in real practice

To analyze the implementation aspects of neural networks and deep learning techniques

To acquire the various applications of artificial intelligence in practical cases.

Jacek M.Zurada, Introduction to Artificial Neural Networks, Jaico Publisher, ND, 2020

E.Rich, K.Knight, S.B.Nair, Artificial Intelligence, McGraw Hill, ND, 2021

Haykin, Neural networks and learning machines, Pearson ND, 2022

M.C.Trivedi, A Classical Approach to Artificial Intelligence, Khanna, ND, 2022

Neural networks, Elsevier