CT79 Soft Computing
Introduction:
Introduction to Soft Computing Concepts, Importance of tolerance in imprecision
and uncertainty, Soft Computing Constituents and Conventional Artificial
Intelligence, From Conventional AI to Computational Intelligence, Fuzzy Set
Theory, Neural Networks and Evolutionary Computation (2
hours)
Fuzzy Sets and Fuzzy Logic: Fuzzy
sets versus Crisp sets, operations on fuzzy sets, Fuzzy Sets and Fuzzy Set
Operations, Multicriteria Decision Making, Fuzzy
Relations and Fuzzy Inference, Fuzzy Rule-based Systems (10 hours)
Artificial Neural Network: The
neuron as a simple computing element, the Perceptron,
Multilayer Neural Networks, Supervised Learning Neural Networks, Unsupervised
Learning Neural Networks, Radial Basis Function Networks, Reinforcement
Learning, Self-Organizing Maps, Adaptive Resonance Theory, Associative
Memories, Applications. (10
hours)
Evolutionary Computation: Genetic
Algorithms and Genetic Programming, Evolutionary Programming, Evolutionary Strategies
and Differential Evolution Coevolution, different
operators of Genetic Algorithms, analysis of selection operations, convergence
of Genetic Algorithms (10
hours)
Rough Sets:
Introduction, Imprecise Categories Approximations and Rough Sets, Reduction of
Knowledge, Decision Tables, and Applications. (6
hours)
Hybrid Systems: Neural-Network-Based
Fuzzy Systems, Fuzzy Logic-Based Neural Networks, Genetic Algorithm for Neural
Network Design and Learning, Fuzzy Logic and Genetic Algorithm for Optimization,
Applications. (4
hours)
References:
Punam: The following template be used to define
syllabus. List broad topics in structure and detailed of each topic in Detailed
Contents section with numbering upto 3 levels. Also
specify total number of hours for a given topic. For you I have expanded two
topics. Also elaborate each topics in detail. If possible add some more topics
if possible.
(reviewed
by Prof Saroj Kaushik)
Structure
1.
Introduction
to soft Computing
2.
Fuzzy
Sets and Fuzzy Logic
3.
Artificial
Neural Network
4.
Evolutionary
Computation
1.
Artificial Neural Network 8
1.1. Introduction
1.2. Neural Network Architectures
1.2.1. Perceptrons
1.2.2. Multilayer Feedforward Networks
1.2.3. Back Propagation Algorithm
1.2.4. Training Algorithms
1.3. Recurrent Network
1.3.1. Hopfield Network
1.3.2. Boltzmann Machines
1.3.3. Radial-Basis Function Networks
1.3.3.1. RBF Architecture
1.3.3.2. RBF network parameters
1.3.3.3. Learning Algorithm
1.4. Radial-Basis Function Networks
1.4.1. RBF Architecture
1.4.2. RBF network parameters
1.4.3. Learning Algorithm
1.4.4. Neural Network Applications
1.4.5. Neural Network Applications
1.5. Learning Neural Networks
1.5.1. Supervised Learning Neural Networks,
1.5.2. Unsupervised Learning Neural Networks,
1.5.3. Reinforcement Learning,
1.5.4. Self-Organizing Maps,
1.5.5. Adaptive Resonance Theory,
1.5.6. Associative Memories
1.6. Neural Network Applications
2.
Evolutionary Computation 5
2.1. Introduction
2.2. Genetic Algorithm
2.2.1. Biological evolutionary process
2.2.2. Search Space
2.2.3. Description of Genetic Algorithm
2.2.4. Operators of GA
2.2.4.1. Various Genetic Operators
2.2.4.2. Encoding schemes for Chromosome
2.3. Applications of GA
2.4. Genetic programming Concepts
2.4.1. Genetic programming
2.5. Evolutionary programming
2.6. Learning Classifier Systems
2.7. Genetic Algorithm and Evolutionary Programming
2.8. Swarm intelligence
2.9. Ant Colony Paradigm
2.9.1. Biological Ant Colony System
2.9.2. Ant colony optimization (ACO)
2.9.3. Simulated Ant Colony Systems
2.9.4. Ant Intelligent Systems
2.9.5. Applications
2.10.Particle Swarm Optimization (PSO)
2.10.1. Optimization algorithm
2.10.2. PSO parameter control
2.10.3. Particle Swarm Intelligent Systems
2.10.4. Applications
Text
books (not more than 3)
Reference
books