Course

Syllabus

Neural networks – Artificial neurons – Activation functions – Learning rules – Supervised and Unsupervised Learning – Single layer and multilayer perceptron – Kohenen’s self-organizing networks – Hopfield networks. Fuzzy systems – Fuzzy sets and relations – Membership functions – Rule base reduction methods – Decision making with fuzzy information – Fuzzy classification and pattern recognition – Neuro-fuzzy systems. Introduction to genetic algorithms – Parent selection – Crossover – Mutation – Genetic Programming – Particle Swarm Optimization – Ant colony optimization – Artificial immune systems – Case Studies – Fuzzy region growing for segmentation of calcifications in mammograms – Classification of normal and ectopic beats using neural networks – Image registration using hybrid bio-inspired approaches. 

Learning Objectives 

LO1 To introduce concepts of Bio-inspired Computing and its applications. LO2 To provide insight on Artificial Neural Networks. 

LO3 To introduce Fuzzy logic and Fuzzy Systems. 

LO4 To provide knowledge on optimization algorithms.

Course Outcomes 

CO1 Ability to understand the principles of bio-inspired algorithms. 

CO2 Ability to apply bio-inspired techniques for pattern recognition and optimization tasks.

CO3 Ability to analyse problems in medical applications using bio-inspired approaches. 

CO4 Ability to evaluate performance of optimization algorithms.

1. Fausett, Laurene V. Fundamentals of neural networks: architectures, algorithms and applications, Pearson Education India, 2006. 
2. Ross, Timothy J. Fuzzy logic with engineering applications. Vol. 2. New York: Wiley, 2004. 
3. Goldberg, David E. Genetic algorithms, Pearson Education India, 2006.