BAMU Final Year AI & ML syllabus

BAMU · Final Year B.E. Artificial Intelligence and Machine Learning · CBCGS

Soft Computing

AIM401 · Semester VII · 4 credits · CT 20 + theory 80

All notes for this subject
  1. Unit 1: Introduction to Soft Computing

    10 hours

    What soft computing is and why it matters, compared with hard computing; its components, applications and scope, and an introduction to machine learning and heuristics.

    Examined in the 80-mark end-semester paper

    • Soft versus hard computing
    • Paradigms of computational intelligence
    • Applications of soft computing
  2. Unit 2: Fuzzy Logic and Fuzzy Systems

    10 hours

    Classical and fuzzy sets, membership functions and fuzzy set operations, fuzzy relations, fuzzification and defuzzification; Mamdani and Sugeno fuzzy inference systems and their use in control and decision making.

    Examined in the 80-mark end-semester paper

    • Fuzzy sets and membership functions
    • Fuzzy relations
    • Fuzzy inference and defuzzification
    • Mamdani and Sugeno fuzzy inference systems
    • Fuzzy logic controllers
  3. Unit 3: Artificial Neural Networks

    10 hours

    Biological and artificial neurons; feed-forward, feedback and recurrent networks; Hebbian, perceptron and delta-rule learning; the multilayer perceptron and backpropagation; ANN applications in pattern recognition and forecasting.

    Examined in the 80-mark end-semester paper

    • Biological and artificial neurons
    • Hebbian, perceptron and delta learning rules
    • Multilayer perceptron and backpropagation
    • Applications of neural networks
  4. Unit 4: Genetic Algorithms

    10 hours

    Fundamentals of evolutionary computing; selection, crossover and mutation; fitness functions and the GA cycle; GA in optimisation and compared with traditional optimisation.

    Examined in the 80-mark end-semester paper

    • Genetic algorithm terminology
    • Encoding in genetic algorithms
    • Selection, crossover and mutation
    • Fitness functions and the GA cycle
    • Genetic algorithms versus traditional optimisation
  5. Unit 5: Hybrid Systems and Applications

    10 hours

    Neuro-fuzzy systems, their architecture and learning; genetic-fuzzy systems; soft computing in real-time systems with case studies in engineering, healthcare, finance and image processing; MATLAB, SciLab and Python tools.

    Examined in the 80-mark end-semester paper

    • Neuro-fuzzy systems
    • Genetic-fuzzy systems
    • Soft computing case studies and tools
  6. Unit 6: Swarm Intelligence and Evolutionary Computing

    10 hours

    Particle swarm optimisation and ant colony optimisation and their applications; other bio-inspired techniques such as bacterial foraging and artificial bee colony.

    Examined in the 80-mark end-semester paper

    • Particle swarm optimisation
    • Ant colony optimisation
    • Bee colony and bacterial foraging algorithms

Unit contents are summarised from the official BAMU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Marathwada University (BAMU).