Unit 1

Artificial Neural Networks – Pattern classification – Single and Multilayer perceptrons – Backpropagation – Pattern Association – Hebbian learning – Hopfield networks – Bidirectional Associative Memory Networks – Competitive learning – Kohenen’s Self Organizing Maps.

Unit 2

Genetic algorithms – Representation – Reproduction – Crossover and Mutation Operators – Crossover and Mutation rates – Selection mechanisms – Fitness proportionate – ranking and tournament selection – Building Block – Hypothesis and Schema Theorem

Unit 3

Swarm Intelligence – Stigmergy – Competition and Cooperation – Particle Swarm Optimization – Anatomy of a particle – Velocity and Position updation– PSO topologies – Control parameters –Ant Colony Optimization – Pheromone updation and evaporation.

• Leandro Nunes De Castro, Fernando Jose Von Zuben, “Recent Developments in Biologically Inspired Computing”, Idea Group Publishing, 2005.
• LaureneFausett, “Fundamentals of neural networks: architectures, algorithms, and applications”, Prentice-Hall, 1994.

• Goldberg, , ” Genetic algorithms in search optimization and machine learning”, Addison Wesley, 1999.
• Xin-She Yang, “Recent Advances in Swarm Intelligence and Evolutionary Computation”, Springer International Publishing, Switzerland, 2015.

Evaluation Pattern

Objectives

• To introduce the characteristics of natural agents and building blocks involved in biological processes
• To provide an understanding on the application of bio inspired algorithms to solve complex problems
• To provide insights into the implementation of bio inspired algorithms

Course Outcomes

• CO1: To understand phenomena guiding biological processes through self-organization and adaptability
• CO2: To visualize the effect of low-level interactions on high-level phenomena
• CO3: To analyze complex engineering problems and solve them by adapting biological processes suitably
• CO4: To design and implement simple bio-inspired algorithms

CO – PO Mapping