RTMNU TY E&TC syllabus

RTMNU · Third Year B.Tech Electronics & Telecommunication Engineering · NEP 2020

Fuzzy Logic and Neural Network

BET6T24-3 · Elective III · Semester VI · 3 credits · College 30 + university 70

One of the Elective III options.

All notes for this subject
  1. Unit 1: Fundamentals of Fuzzy Logic

    7 hours

    Crisp and fuzzy sets, complements, unions, intersections and aggregation operations; fuzzy relations, compatibility and orderings, morphisms, fuzzy relational equations and fuzzy systems.

    Examined in the 70-mark end-semester paper

    • Fuzzy sets and operations
    • Fuzzy relations and composition
  2. Unit 2: Architecture of Neural Networks

    7 hours

    Biological and artificial neurons, weights, biases and activation functions, learning rules, the McCulloch–Pitts model, the perceptron, linear separability, Hebbian learning, the convergence theorem and the delta rule.

    Examined in the 70-mark end-semester paper

    • Biological and artificial neurons
    • Activation functions
    • McCulloch-Pitts neuron model
    • Single-layer perceptron
    • Linear separability and the XOR problem
    • Learning rules: Hebbian and delta
  3. Unit 3: Basic Neural Network Techniques

    8 hours

    The backpropagation network, learning rules, associative memory, bidirectional associative memory, Hopfield networks, Boltzmann machines and applications.

    Examined in the 70-mark end-semester paper

    • Multilayer perceptron
    • Error backpropagation
    • Hopfield networks and associative memory
    • Bidirectional associative memory
    • Boltzmann machine and Boltzmann learning
  4. Unit 4: Competitive Neural Networks

    7 hours

    Competitive learning, fixed-weight networks, Kohonen self-organising maps, learning vector quantisation, counter-propagation networks, and ART1 and ART2.

    Examined in the 70-mark end-semester paper

    • Competitive learning
    • Kohonen self-organising maps
    • Learning vector quantisation
    • Counter-propagation networks
    • Adaptive resonance theory: ART1 and ART2
  5. Unit 5: Special Neural Networks

    7 hours

    The cognitron and neocognitron and their training, fuzzy associative memories, fuzzy system architecture, and fuzzy versus neural systems.

    Examined in the 70-mark end-semester paper

    • Cognitron and neocognitron
    • Fuzzy associative memories
    • Fuzzy inference systems

Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).