Mumbai University BE EXTC syllabus

Mumbai University · Final Year Electronics and Telecommunication Engineering · Rev-2019 'C' Scheme

Deep Learning

ECCDLO7012 · Department Optional Course 3 · Semester VII · 3 credits · Internal tests 20 (average of two) + end-semester 80

End-semester paper (3 hours): Six questions of 20 marks; Q1 is compulsory and you answer four. Each module's share of the paper follows its lecture hours.

One of the Department Optional Course 3 options.

All notes for this subject
  1. Module 1: Introduction to Deep Learning

    3 hours

    History of deep learning; deep feedforward networks; gradient-based learning and hidden units; architecture design; backpropagation.

    Examined in the 80-mark end-semester paper (about 8% of it, by lecture hours); the class tests cover what has been taught by then

    • Deep feedforward networks
    • Backpropagation algorithm
  2. Module 2: TensorFlow for Deep Learning

    6 hours

    Computational graphs; regression and gradient descent in TensorFlow; TensorBoard; Keras; preprocessing and augmenting image data.

    Examined in the 80-mark end-semester paper (about 15% of it, by lecture hours); the class tests cover what has been taught by then

    • TensorFlow basics
    • Keras and PyTorch
    • Image preprocessing and augmentation
  3. Module 3: Regularisation and Optimisation

    6 hours

    L1, L2, early stopping and dropout; challenges in optimisation; initialisation; AdaGrad, RMSProp and Adam; batch normalisation.

    Examined in the 80-mark end-semester paper (about 15% of it, by lecture hours); the class tests cover what has been taught by then

    • Overfitting, dropout and regularisation
    • Optimisers: AdaGrad, RMSProp and Adam
    • Batch normalisation
  4. Module 4: Evolution of CNNs

    8 hours

    LeNet, AlexNet, VGG, GoogLeNet, ResNet and U-Net compared; evaluation; image classification and object detection.

    Examined in the 80-mark end-semester paper (about 21% of it, by lecture hours); the class tests cover what has been taught by then

    • CNN architectures: LeNet, AlexNet and VGG
    • ResNet and DenseNet
    • GoogLeNet and U-Net
    • Image classification and detection
  5. Module 5: Sequence Modelling

    8 hours

    Recurrent, recursive and bidirectional nets; encoder–decoder architectures; LSTM and GRU; image captioning and time-series forecasting.

    Examined in the 80-mark end-semester paper (about 21% of it, by lecture hours); the class tests cover what has been taught by then

    • Recurrent neural networks
    • LSTM and GRU
    • Sequence-to-sequence models
  6. Module 6: Encoder–Decoder Models

    8 hours

    Autoencoders and manifold learning; sparse, denoising and contractive autoencoders; deep autoencoders; variational autoencoders and the reparameterisation trick; applications.

    Examined in the 80-mark end-semester paper (about 21% of it, by lecture hours); the class tests cover what has been taught by then

    • Autoencoders and RBMs
    • Sparse, denoising and contractive autoencoders
    • Variational autoencoders

Module contents are summarised from the official Mumbai University syllabus . AiCanCode.org is not affiliated with the University of Mumbai.