1. Introduction to artificial neural networks 

1.1. Biological neural networks
1.2. Pattern analysis tasks: Classification, Regression, Clustering
1.3. Computational models of neurons
1.4. Structures of neural networks
1.5. Learning principles

2. Linear models for regression and classification 

2.1. Polynomial curve fitting
2.2. Bayesian curve fitting
2.3. Linear basis function models
2.5. Bias-variance decomposition
2.6. Bayesian linear regression
2.7. Least squares for classification
2.8. Logistic regression for classification
2.9. Bayesian logistic regression for classification

3. Feedforward neural networks 

3.1. Pattern classification using perceptron
3.2. Multilayer feedforward neural networks (MLFFNNs)
3.3. Pattern classification and regression using MLFFNNs
3.4. Error backpropagation learning
3.5. Fast learning methods: Conjugate gradient method
3.6. Autoassociative neural networks
3.7. Bayesian neural networks

4. Radial basis function networks 

4.1. Regularization theory
4.2. RBF networks for function approximation
4.3. RBF networks for pattern classification

5. Kernel methods for pattern analysis

5.1. Statistical learning theory
5.2. Support vector machines for pattern classification
5.3. Support vector regression for function approximation
5.4. Relevance vector machines for classification and regression

6. Self-organizing maps 

6.1. Pattern clustering
6.2. Topological mapping
6.3. Kohonen’s self-organizing map

7. Feedback neural networks 

7.1. Pattern storage and retrieval
7.2. Hopfield model
7.3. Boltzmann machine
7.4. Recurrent neural networks

Text Books: 

1. B.Yegnanarayana, Artificial Neural Networks, Prentice Hall of India, 1999 

2. Satish Kumar, Neural Networks – A Classroom Approach, Tata McGraw-Hill, 2003 

3. S.Haykin, Neural Networks – A Comprehensive Foundation, Prentice Hall, 1998 

4. C.M.Bishop, Pattern Recognition and Machine Learning, Springer, 2006 

Evaluation method: