B.E Artificial Intelligence and Machine Learning Deep Learning Syllabus - Mumbai University
This is the Fourth Year AI-ML syllabus under REV-2019 'C' Scheme, in force from the academic year 2023-24. The University has not yet published an NEP 2020 syllabus for this year of the degree, and this is the scheme its examinations are set on.
The University's own credit and examination tables for this year print the name as “Deep Leaning”. The syllabus block itself, and the rest of the document, print “Deep Learning”, which is the name used here.
Loading syllabus...
Syllabus for Deep Learning
Module 1: 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: Training, Optimization and Regularization of Deep Neural Network
- 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 Optimization Learning with backpropagation, Learning Parameters: Gradient Descent (GD), Stochastic and Mini Batch GD, Momentum Based GD, Nesterov Accelerated GD, AdaGrad, Adam, RMSProp 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: 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: 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: 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: Recent Trends and Applications
- 6.1 Generative Adversarial Network (GAN): Architecture
- 6.2 Applications: Image Generation, DeepFake
Useful Links
- 1 Ian Goodfellow, Yoshua Bengio, Aaron Courville. ―Deep Learningǁ, MIT Press Ltd, 2016
- 2 Li Deng and Dong Yu, ―Deep Learning Methods and Applicationsǁ, Publishers Inc.
- 3 Satish Kumar "Neural Networks A Classroom Approach" Tata McGraw-Hill.
- 4 JM Zurada ―Introduction to Artificial Neural Systemsǁ, Jaico Publishing House
- 5 M. J. Kochenderfer, Tim A. Wheeler. ―Algorithms for Optimizationǁ, MIT Press.
- 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 Cookbookǁ, 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
- 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 Machine Learning) under REV-2019 'C' Scheme, in force from the academic year 2023-24. Wording is as printed in that syllabus. Module numbering is as printed there too.
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.