M.Sc. CSIT Syllabus

Neural Networks

Course Title: Neural Networks
Full Marks: 45 + 30
Course No: C.Sc. 543
Pass Marks: 22.5 + 15
Nature of the Course: Theory + Lab
Credit Hrs: 3

Course Description:

This course deals with resembling the conscious behavior of brain in an artificially connected logical nodes that can learn itself in a supervised and unsupervised environment. It introduces linear algebra for creating and processing input patterns to generate output. It also emphasizes on probabilistic model for classification and prediction within a tolerable and significant limit.

Unit 1: Introduction to artificial neural networks 5 hrs

Biological neural networks; Pattern analysis tasks: Classification, Regression, Clustering; Computational models of neurons; Structures of neural networks; Learning principles

Unit 2: Linear models for regression and classification 7 hrs

Polynomial curve fitting; Bayesian curve fitting; Linear basis function models; Bias-variance decomposition; Bayesian linear regression; Least squares for classification; Logistic regression for classification; Bayesian logistic regression for classification

Unit 3: Feed forward neural networks 7 hrs

Pattern classification using perception; Multi layer feed forward neural networks (MLFFNNs); Pattern classification and regression using MLFFNNs; Error back propagation learning; Fast learning methods: Conjugate gradient method; Auto associative neural networks; Bayesian neural networks

Unit 4: Radial basis function networks 8 hrs

Regularization theory; RBF networks for function approximation; RBF networks for pattern classification

Unit 5: Kernel methods for pattern analysis 8 hrs

Statistical learning theory; Support vector machines for pattern classification; Support vector regression for function approximation; Relevance vector machines for classification and regression

Unit 6: Self-organizing maps 5 hrs

Pattern clustering; Topological mapping; Kohonen’s self-organizing map

Unit 7: Feedback neural networks 5 hrs

Pattern storage and retrieval; Hopfield model; Boltzmann machine; 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
About Author

Prince Pudasaini