SUK · Third Year B.Tech. Computer Science and Engineering (Data Science) · NEP 2020
Soft Computing
DS3204 · Elective II · Semester VI · 3 credits · ISE 10 + mid-semester 30 + ESE 60
One of the Elective II options.
Unit 1: Introduction to Soft Computing
5 hoursWhat soft computing is, its need, characteristics and applications; its tools: fuzzy logic, neural networks and evolutionary computing.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Soft versus hard computing
- Paradigms of computational intelligence
- Applications of soft computing
Unit 2: Fuzzy Systems
8 hoursFuzzy sets, membership functions and relations; defuzzification, fuzzy arithmetic and measures; fuzzy rule bases and approximate reasoning; fuzzy decision making and fuzzy logic controller design.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Fuzzy sets and membership functions
- Fuzzy relations
- Linguistic variables and fuzzy rules
- Fuzzy inference and defuzzification
- Fuzzy logic controllers
Unit 3: Artificial Neural Networks
8 hoursLearning rules and activation functions; single-layer perceptrons; back-propagation networks and learning and their variations; associative memory, adaptive resonance theory and self-organising maps.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Biological and artificial neurons
- Hebbian, perceptron and delta learning rules
- Multilayer perceptron and backpropagation
- Hopfield networks and bidirectional associative memory
- Adaptive resonance theory: ART1 and ART2
- Kohonen self-organising maps
Unit 4: Genetic Algorithms
7 hoursHistory and working principle of GAs; encoding methods and the fitness function; reproduction, crossover and mutation; convergence, bit-wise operations and multi-level optimisation.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Genetic algorithm terminology
- Encoding in genetic algorithms
- Fitness functions and the GA cycle
- Selection, crossover and mutation
Unit 5: Hybrid Systems
7 hoursSequential, auxiliary and embedded hybrid systems; neuro-fuzzy, neuro-genetic and fuzzy-genetic hybrids.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Neuro-fuzzy systems
- Genetic-fuzzy systems
Unit 6: Multi-Objective Optimisation Problem Solving
6 hoursMulti-objective optimisation problems and the issues in solving them; multi-objective evolutionary algorithms; non-Pareto and Pareto-based approaches and their applications.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Constraint handling and multi-objective evolution
Unit contents are summarised from the official SUK syllabus . AiCanCode.org is not affiliated with Shivaji University, Kolhapur.