DS4018 Artificial Intelligence and Optimization Techniques Syllabus:

DS4018 Artificial Intelligence and Optimization Techniques Syllabus – Anna University PG Syllabus Regulation 2021

COURSE OBJECTIVES:

 To introduce the techniques of computational methods inspired by nature, such as neural networks, genetic algorithms and other evolutionary computation systems, ant swarm optimization and artificial immune systems.
 To present the main rules underlying these techniques.
 To present selected case-studies.
 To adopt these techniques in solving problems in the real world.

UNIT I NEURAL NETWORKS

Neural Networks: Back Propagation Network, generalized delta rule, Radial Basis Function Network, interpolation and approximation RBFNS, comparison between RBFN and BPN, Support Vector Machines: Optimal hyperplane for linearly separable patterns, optimal hyperplane for nonlinearly separable patterns, Inverse Modeling.

UNIT II FUZZY LOGIC SYSTEMS

Fuzzy Logic System: Basic of fuzzy logic theory , crisp and fuzzy sets, Basic set operation like union , interaction , complement , T-norm , T-conorm , composition of fuzzy relations, fuzzy if-then rules , fuzzy reasoning, Neuro-Fuzzy Modeling: Adaptive Neuro-Fuzzy Inference System (ANFIS) , ANFIS architecture , Hybrid Learning Algorithm.

UNIT III EVOLUTIONARY COMPUTATION & GENETIC ALGORITHMS

Evolutionary Computation (EC) – Features of EC – Classification of EC – Advantages – Applications. Genetic Algorithms: Introduction – Biological Background – Operators in GA-GA Algorithm – Classification of GA – Applications

UNIT IV ANT COLONY OPTIMIZATION

Ant Colony Optimization: Introduction – From real to artificial ants- Theoretical considerations – Convergence proofs – ACO Algorithm – ACO and model based search – Application principles of ACO.

UNIT V PARTICLE SWARM OPTIMIZATION

Particle Swarm Optimization: Introduction – Principles of bird flocking and fish schooling – Evolution of PSO – Operating principles – PSO Algorithm – Neighborhood Topologies – Convergence criteria – Applications of PSO, Honey Bee Social Foraging Algorithms, Bacterial Foraging Optimization Algorithm.

PRACTICAL EXERCISES: 30 PERIODS

1. Data preprocessing and annotation and creation of datasets.
2. Learn existing datasets and Treebanks
3. Implementation of searching techniques in AI.
4. Implementation of Knowledge representation schemes.
5. Natural language processing tool development.
6. implement DFS and BFS
7. solution for travelling salesman Problem
8. implement Simulated Annealing Algorithm.
9. implement Hill Climbing Algorithm
10. implement Honey Bee Social Foraging Algorithms

COURSE OUTCOMES:

CO1: Ability to design and train neural networks with different rules
CO2: Ability to devise fuzzy logic rules
CO3: Ability to implement genetic algorithms
CO4: Ability to implement ANT colony optimization technique for various problems
CO5: Ability to use PSO technique

TOTAL:75 PERIODS

REFERENCES:

1. Wolfgang Ertel, “Introduction to Artificial Intelligence”, Springer, 2nd Edition, 2017
2. NelloCristianini, John Shawe-Taylor, “An Introduction to Support Vector Machines and Other Kernel-based Learning Methods”,Cambridge University Press. 2013
3. Christopher M. Bishop, “Neural Networks for Pattern Recognition”, Oxford University Press, 2005
4. H.-J. Zimmermann, “Fuzzy Set Theory and its Applications”, Springer Science+Business Media New York, 4th edition, 2006
5. David E. Goldberg, “Genetic Algorithms in search, Optimization & Machine Learning”, Pearson Education, 2006
6. Kenneth A DeJong,“Evolutionary Computation A Unified Approach”, Prentice Hall of India, New Delhi, 2006.
7. Marco Dorigo and Thomas Stutzle, “Ant Colony optimization”, Prentice Hall of India, New Delhi, 2004.
8. N P Padhy, “Artificial Intelligence and Intelligent Systems”, Oxford University Press, 2005.
9. Engelbrecht, A.P., “Fundamentals of Computational Swarm Intelligence”, Wiley, 2005.