Scribd Logo
Upload

Welcome to Scribd!

  • 12 views

    Uei815e NNFL

    Uploaded by

    Vaibhav Patil
    This document outlines a course on neural networks and fuzzy logic. It covers 3 credits over 40 hours, divided into 4 units - introduction to neural networks and learning processes, introduction to fuzzy logic, fuzzy sets and relations, and fuzzy control systems. The objectives are to provide understanding of neural network and fuzzy logic theories, and discuss architectures, algorithms and applications.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Uei815e NNFL

    Uploaded by

    Vaibhav Patil
    12 views2 pages
    This document outlines a course on neural networks and fuzzy logic. It covers 3 credits over 40 hours, divided into 4 units - introduction to neural networks and learning processes, introduction to fuzzy logic, fuzzy sets and relations, and fuzzy control systems. The objectives are to provide understanding of neural network and fuzzy logic theories, and discuss architectures, algorithms and applications.

    Original Description:

    Neural Networks

    Original Title

    UEI815E_NNFL

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document outlines a course on neural networks and fuzzy logic. It covers 3 credits over 40 hours, divided into 4 units - introduction to neural networks and learning processes, introduction to fuzzy logic, fuzzy sets and relations, and fuzzy control systems. The objectives are to provide understanding of neural network and fuzzy logic theories, and discuss architectures, algorithms and applications.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    12 views2 pages

    Uei815e NNFL

    Uploaded by

    Vaibhav Patil
    This document outlines a course on neural networks and fuzzy logic. It covers 3 credits over 40 hours, divided into 4 units - introduction to neural networks and learning processes, introduction to fuzzy logic, fuzzy sets and relations, and fuzzy control systems. The objectives are to provide understanding of neural network and fuzzy logic theories, and discuss architectures, algorithms and applications.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    UEI815E: NEURAL NETWORKS and FUZZY LOGIC

    3 Credits (3-0-0)
    Course Objectives:
    1. To provide basic understanding of neural network theory and fuzzy logic
    theory.

    2. Discuss neural networks and fuzzy systems, architectures, algorithms


    and applications.

    3. To teach about the concept of fuzziness involved in various systems and


    provide adequate knowledge about fuzzy set theory, and fuzzy logic

    UNIT-I
    Introduction: What is neural network, Human brain, Models of neuron,
    Neural network viewed as directed graphs, Feedback, Network architecture,
    Knowledge representation, Artificial Intelligence and Neural networks
    10 Hrs

    UNIT-II
    Learning Process: Introduction, Error correction learning, Memory based
    learning, Hebbian learning, Competitive learning, Boltzmann learning, Credit
    assignment problem, Learning with a teacher, Learning without teacher,
    Learning tasks, Sigle layer perceptron, Multilayer perceptron

    10 Hrs.
    UNIT-III
    Introduction to Fuzzy Logic: Introduction, uncertainty and imprecision,
    statistics and random process, uncertainty in information, fuzzy sets and
    membership, Classical and Fuzzy sets: classical sets, operation on classical
    sets, properties of classical sets, mapping of classical sets to function, fuzzy set
    operation, properties of fuzzy sets, sets as points in Hypercubes. Classical
    Relations and Fuzzy relations: Cartesian product
    10 Hrs.
    UNIT-IV
    Crisp relations, fuzzy relations, tolerance and equivalence relations, fuzzy
    tolerance and equivalence relations, membership function: feature of
    membership function, fuzzification, membership value assignment: intuition,
    inference, rank ordering, angular fuzzy sets, inductive reasoning,
    defuzzification methods, Fuzzy control systems: Control system design stages,
    assumptions in a fuzzy control system design stage, simple fuzzy logic
    controllers, general fuzzy logic controllers, examples of fuzzy control system
    design.
    10 Hrs.
    Total Hrs.: 40
    Course Outcomes:
    Student will be able to:

    CO1: Analyze the working of biological neural network & the artificial
    neural networks.

    CO2: Characterize the learning algorithms as supervised learning and


    unsupervised learning and analyze the various algorithms of
    supervised and unsupervised learning

    CO3: Understand the basic ideas of fuzzy sets, operations and


    properties of fuzzy sets

    CO4: Analyze the application of fuzzy logic control to real time


    systems.

    Text Books:
    1. Simon Haykin, “Neural Networks-A Compressive Foundation”, 2nd
    Edition, Pearson Education.
    2. Timothy J Ross, “Fuzzy Logic with Engineering Applications”, McGraw
    Hill International Edition.
    3. James A Anderson, “An Introduction to Neural Networks”, Prentice Hall
    of India.
    Reference Books:
    1. S. Rajasekaran, G. A. Vijayalaksmi Pai “Neural Networks, Fuzzy Logic,
    and Genetic Algorithms”, Eastern Economic Edition

    You might also like