DBATU · Final Year B.Tech Information Technology · Non-NEP
Soft Computing
BTITE703B · Elective I · Semester VII · 3 credits · Continuous assessment 20 + mid-semester 20 + end-semester 60
One of the Elective I options.
Unit 1: Artificial Neural Networks I
Biological and artificial neurons; bias and threshold; the McCulloch–Pitts model and AND, OR and XOR; learning paradigms; the linear neuron, gradient descent and activation functions; Hebbian and delta learning; the perceptron and its limits.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Artificial neuron model
- McCulloch–Pitts neuron and logic functions
- Learning rules: Hebbian and delta
- Perceptron, Adaline and Madaline
Unit 2: Artificial Neural Networks II
The multilayer perceptron and backpropagation; self-organising feature maps; learning vector quantisation; radial basis function networks; Hopfield networks and auto- and hetero-associative memory; a brief look at deep, convolutional and recurrent networks.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Backpropagation networks
- Kohonen self-organising maps
- Learning vector quantization
- Radial basis function networks
- Hopfield networks
- Associative memory
- Deep, convolutional and recurrent networks: an introduction
Unit 3: Fuzzy Logic I
Basic concepts; fuzzy and crisp sets; fuzzy set theory, operations and properties; fuzzy and crisp relations; fuzzy-to-crisp conversion.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Fuzzy sets and relations
- Fuzzy set operations and properties
- Lambda-cuts and fuzzy-to-crisp conversion
Unit 4: Fuzzy Logic II
Membership functions; inference in fuzzy logic; fuzzy if-then rules, implications and algorithms; fuzzification and defuzzification; the fuzzy controller and industrial applications.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Membership functions and fuzzification
- Fuzzy if-then rules and implications
- Mamdani and Sugeno inference
- Defuzzification methods
- Fuzzy logic controllers
Unit 5: Evolutionary Computation
Genetic algorithms: survival of the fittest, fitness computation, crossover, mutation and reproduction; rank and rank-space methods; simulated annealing; ant colony and particle swarm optimisation.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Genetic algorithm operators
- Crossover and mutation
- Fitness and selection: rank and rank-space methods
- Simulated annealing and tabu search
- Ant colony and particle swarm optimisation
Unit contents are summarised from the official DBATU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Technological University (DBATU).