Eight Semester January-2025

Department of Electronics and Communication Engineering

B. Tech in Electronics and Communication Engineering

Semester

Eighth

Subject Title

Neural Networks & Machine Learning

Code

TEC 856

Course Component

Credits

Contact Hours

L

T

P

Program Elective Course (PEC) (VI)

03

3

0

0

Examination Duration (Hrs)

Theory

Weightage: Evaluation

CWA

MSE

ESE

03

25

25

50

Pre-requisite: Basic Probability Theory and Basic Linear Algebra

Course Outcomes

Upon completion of this course, the students will be able to

CO 1          

Understand the basics of neural network and its parameters.

CO 2          

Examine the feed forward network and its implementation.

CO 3          

Analyse the concepts of pattern analysis and implementation of support vector machine.

CO 4          

Investigate self-organizing map and pattern clustering.

CO 5          

Evaluate different feedback network, such as Hopfield, Boltzmann machine.

CO 6          

Develop neural network for specific applications.

Unit No.

Content

Hours

Unit 1:    

Introduction to Artificial Neural Networks:

Biological neural networks, ANN application overview, Pattern analysis tasks: Classification, Regression and clustering, Computational models of neurons, Structures of neural networks, Learning principles, Supervised, Unsupervised and reinforcement learning.

Linear Models of Learning and Classification:

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.

12

Unit 2:    

Feed Forward Neural Networks:

Pattern classification using perceptron, Multilayer feed forward neural networks (MLFNNs), Pattern classification using MLFNNs, error and back propagation learning, Fast learning methods: Conjugate gradient method, Auto-associative neural networks, Bayesian neural networks.

8

Unit 3:    

Radial Basis Function Networks:

Regularization theory, RBF networks for function approximation, RBF networks for pattern classification.

Kernel Methods for Pattern Analysis:

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

8

Unit 4:    

Self-Organizing Maps:

Pattern clustering, Topological mapping, Kohonen’s self organizing map, Competitive learning, Learning vector quantizers, Counter propagation networks, Adaptive Resonance Theory (ART).

6

Unit 5:    

Feedback Neural Networks:

Pattern storage and retrieval, Hopfield model, Boltzmann machine, Recurrent neural networks.

Applications of Neural Networks and Machine Learning:

Case studies.

6

Total Hours

42