Scribd Logo
Upload

Welcome to Scribd!

  • 1 views

    NEURAL NETWORK

    Uploaded by

    Ankit Kumar

    Copyright:

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

    NEURAL NETWORK

    Uploaded by

    Ankit Kumar
    1 views2 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

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

    NEURAL NETWORK

    Uploaded by

    Ankit Kumar

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 2

    BCSE0706: NEURAL NETWORK

    Objective: Students will get an insight of the Neural Network approaches. Providing students, the
    mathematical background to carry out optimization.

    Credits: 03 L–T–P-J: 3–0–0-0


    Module Teaching
    Content
    No. Hours
    Neural Networks: Fundamentals of Artificial Neural Network (ANN), Human
    Brain, Supervised Vs Unsupervised Learning, Models of ANN, ANN models:
    Rosenblatt’s Perception, McCulloch & Pitts Model, Single Layer Perceptron,
    Learning Methods in Perceptron, Linearly Separable Task and XOR Problem,
    I. Multi-Layer Perceptron, ADALINE, MADALINE Network
    20
    Multilayered Neural Architecture: Activation functions (ReLU, Sigmoid,
    tanh, etc.), Gradient Descent, Back Propagation (BP) Learning, learning rate,
    momentum, Loss Function in Neural Network, Optimizers in Neural
    Networks, Hessian Matrix, Heuristics for making Back-Propagation algorithm
    perform better, Applications of Neural Network. Radial Basis Neural Network
    Probabilistic Models: Probabilistic Models, Maximum Likelihood Estimation,
    Linear Regression, Logistic Regression
    Deep Learning: AI vs ML vs DL, Deep learning capabilities, Data Pre-
    processing, training and testing, confusion matrix. Bias and Variance,
    II. Vanishing gradients.
    20
    Convolutional Neural Network (CNN)- Basic terminologies in CNN
    (Convolution, Filter/Kernel, Padding, Pooling), Architecture of CNN, Different
    Models of CNN, Classification of MNIST dataset images with CNN.
    Recurrent Neural Networks (RNN): Sequential Processing, Stability Gated
    Nets- LSTM (Long Short-Term Memory), Gated Recurrent Unit), Examples.

    Text Books:
     Haykin, Simon. Neural networks and learning machines, 3/E. Pearson Education India, 2010.
     Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, An MIT Press book, 2016
    http://www.deeplearningbook.org

    Reference Books:
     Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition by Aurélien
    Géron, 2019, Publisher(s): O'Reilly Media, Inc.
     Joel Grus, Data Science from Scratch 2e: First Principles with Python, O′Reilly; 2nd edition, 2019.
     S. Rajsekaran& G.A. VijayalakshmiPai, “Neural Networks, Fuzzy Logic and Genetic Algorithm:
    Synthesis and Applications”, 4th Edition, Prentice Hall of India,2003.

    Outcome: After completion of course, student will be able to:


    S.no CO Objective
    1 CO1 Understand the differences between networks for supervised and unsupervised learning

    2 CO2 Design single and multi-layer Perceptron neural networks

    3 CO3 Understand Back Propagation Non-Linear Neural network architecture

    4 CO4 Understand Convolutional Neural Network and Recurrent Neural Network


    BCSE0736: NEURAL NETWORK LAB

    Objective: Students will get an insight of the Neural Network approaches. Providing students, the
    mathematical background to carry out optimization.

    Credits: 01 L–T–P-J: 0–0–2-0


    Module Teaching
    Content
    No. Hours

     Programming setup
     Python library introduction
     Plot activation functions and their derivatives
     Generate AND NOT function using McCulloch-Pitts neural net
    I, II  Generate XOR function using McCulloch-Pitts neuron. 24
     Linear Regression, Logistic Regression
     Back Propagation Network for XOR function
     Multi-Layer Perceptron
     Training CNN
     Training RNN

    Text Books:
     Haykin, Simon. Neural networks and learning machines, 3/E. Pearson Education India, 2010.
     Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, An MIT Press book, 2016
    http://www.deeplearningbook.org

    Reference Books:
     Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition by Aurélien
    Géron, 2019, Publisher(s): O'Reilly Media, Inc.
     Joel Grus, Data Science from Scratch 2e: First Principles with Python, O′Reilly; 2nd edition, 2019.
     S. Rajsekaran& G.A. VijayalakshmiPai, “Neural Networks, Fuzzy Logic and Genetic Algorithm:
    Synthesis and Applications”, 4th Edition, Prentice Hall of India,2003.

    You might also like