munotes®
Sign in
Home / Syllabus / B.E. (Artificial Intelligence and Data Science) / Fourth Year BE AI and DS / Semester 7 / Deep Learning

B.E. (Artificial Intelligence and Data Science) Deep Learning Syllabus - Mumbai University

This is the Fourth Year BE AI and DS syllabus under CBCS REV-2019 'C' Scheme, in force from the academic year 2023-24. The University has published no NEP 2020 syllabus for Semesters V to VIII of any engineering branch, so this is the scheme you are examined on — exam form 1T01817 and 1T01818. The first and second years of the degree are on NEP 2020.

Deep Learning.pdf
Semester 7 · Fourth Year BE AI and DS · 3 credits · CBCS REV-2019 'C' Scheme

Loading syllabus...

Syllabus for Deep Learning

Semester 7 · Fourth Year BE AI and DS · 3 credits · CBCS REV-2019 'C' Scheme

Module 1 4 hours

  • Fundamentals of Neural Network
  • 1.1 History of Deep Learning, Deep Learning Success Stories, Multilayer Perceptrons (MLPs), Representation Power of MLPs, Sigmoid Neurons, Gradient Descent, Feedforward Neural Networks, Representation Power of Feedforward Neural Networks
  • 1.2 Deep Networks: Three Classes of Deep Learning Basic Terminologies of Deep Learning

Module 2 10 hours

  • Training, Optimization and Regularization of Deep Neural Network
  • 2.1 Training Feedforward DNN Multi Layered Feed Forward Neural Network, Learning Factors, Activation functions: Tanh, Logistic, Linear, Softmax, ReLU, Leaky ReLU, Loss functions: Squared Error loss, Cross Entropy, Choosing output function and loss function
  • 2.2 Optimization Learning with backpropagation, Learning Parameters: Gradient Descent (GD), Stochastic and Mini Batch GD, Momentum Based GD,
  • Nesterov Accelerated GD, AdaGrad, Adam, RMSProp
  • 2.3 Regularization Overview of Overfitting, Types of biases, Bias Variance Tradeoff Regularization Methods: L1, L2 regularization, Parameter sharing, Dropout, Weight Decay, Batch normalization, Early stopping, Data Augmentation, Adding noise to input and output

Module 3 6 hours

  • Autoencoders: Unsupervised Learning
  • 3.1 Introduction, Linear Autoencoder, Undercomplete Autoencoder, Overcomplete Autoencoders, Regularization in Autoencoders
  • 3.2 Denoising Autoencoders, Sparse Autoencoders, Contractive Autoencoders
  • 3.3 Application of Autoencoders: Image Compression

Module 4 7 hours

  • Convolutional Neural Networks (CNN): Supervised Learning
  • 4.1 Convolution operation, Padding, Stride, Relation between input, output and filter size, CNN architecture: Convolution layer, Pooling Layer, Weight Sharing in CNN, Fully Connected NN vs CNN, Variants of basic Convolution function, Multichannel convolution operation,2D convolution.
  • 4.2 Modern Deep Learning Architectures: LeNET: Architecture, AlexNET: Architecture, ResNet : Architecture

Module 5 8 hours

  • Recurrent Neural Networks (RNN)
  • 5.1 Sequence Learning Problem, Unfolding Computational graphs, Recurrent Neural Network, Bidirectional RNN, Backpropagation Through Time (BTT), Limitation of " vanilla RNN" Vanishing and Exploding Gradients, Truncated BTT
  • 5.2 Long Short Term Memory(LSTM): Selective Read, Selective write, Selective Forget, Gated Recurrent Unit (GRU)

Module 6 4 hours

  • Recent Trends and Applications
  • 6.1 Generative Adversarial Network (GAN): Architecture
  • 6.2 Applications: Image Generation, DeepFake

Text Books

  • 1 Ian Goodfellow, Yoshua Bengio, Aaron Courville. "Deep Learning", MIT Press Ltd, 2016
  • 2 Li Deng and Dong Yu, "Deep Learning Methods and Applications", Publishers Inc.
  • 3 Satish Kumar "Neural Networks A Classroom Approach" Tata McGraw-Hill.
  • 4 JM Zurada "Introduction to Artificial Neural Systems", Jaico Publishing House
  • 5 M. J. Kochenderfer, Tim A. Wheeler. "Algorithms for Optimization", MIT Press.

References

  • 1 Deep Learning from Scratch: Building with Python from First Principles- Seth Weidman by O`Reilley
  • 2 François Chollet. "Deep learning with Python "(Vol. 361). 2018 New York: Manning.
  • 3 Douwe Osinga. "Deep Learning Cookbook", O'REILLY, SPD Publishers, Delhi.
  • 4 Simon Haykin, Neural Network- A Comprehensive Foundation- Prentice Hall International, Inc
  • 5 S.N.Sivanandam and S.N.Deepa, Principles of soft computing-Wiley India

Useful Links

  • 1 http://www.cse.iitm.ac.in/~miteshk/CS6910.html
  • 2 https://nptel.ac.in/courses/106/106/106106184/
  • 3 https://www.deeplearningbook.org/

Reproduced from the University of Mumbai syllabus for B.E. (Artificial Intelligence and Data Science), item 6.12 (N), under CBCS REV-2019 'C' Scheme, in force from the academic year 2023-24. Wording, module numbering and hours are as printed in that syllabus.

The complete syllabus

This subject is cut from the University circular for its year. Open a document here if you want the whole thing rather than a single subject.

PDF B.E. Artificial Intelligence and Data Science - First Year, Semester I and II - NEP 2020 - Item 7.7 (R-A) NEP 2020, Semesters I and II, in force from 2024-25 Read full PDF Read
PDF B.E. Artificial Intelligence and Data Science - Second Year, Semester III and IV - NEP 2020 - Item 6.20 (N) NEP 2020, Semesters III and IV, in force from 2025-26 Read full PDF Read
PDF B.E. Artificial Intelligence and Data Science - Third Year, Semester V and VI - CBCS REV-2019 C Scheme - Item 6.42 (R) CBCS REV-2019 'C' Scheme, Semesters V and VI, in force from 2022-23 Read full PDF Read
PDF B.E. Artificial Intelligence and Data Science - Fourth Year, Semester VII and VIII - CBCS REV-2019 C Scheme - Item 6.12 (N) CBCS REV-2019 'C' Scheme, Semesters VII and VIII, in force from 2023-24 Read full PDF Read
Report or request
Done!