SPPU BE E&TC syllabus

SPPU · Final Year Electronics & Telecommunication Engineering · 2019 Course

Deep Learning

404185C · Elective IV · Semester VII · 3 credits · In-semester 30 + end-semester 70

One of the Elective IV options.

All notes for this subject
  1. Unit 1: Machine Learning

    6 hours

    Types of machine learning; linear regression; logistic regression and classification; decision trees and random forests; naive Bayes and SVMs; applications.

    Marks: 15 in the in-semester exam

    • Types of machine learning
    • Linear and logistic regression
    • Decision trees and random forests
    • Naive Bayes and SVM
  2. Unit 2: Deep Learning and Frameworks

    6 hours

    Perceptrons, multilayer perceptrons and ANN architecture; TensorFlow variables, operations and placeholders; CPU and GPU; logistic regression in TensorFlow; Keras and PyTorch.

    Marks: 15 in the in-semester exam

    • Perceptron and multilayer perceptron
    • TensorFlow basics
    • Keras and PyTorch
  3. Unit 3: Deep Learning Architecture

    6 hours

    Width and depth; activation functions; batch normalisation; overfitting and generalisation; dropout and regularisation; unsupervised training; restricted Boltzmann machines; autoencoders.

    Marks: 17–18 in the end-semester exam

    • Activation functions
    • Batch normalisation
    • Overfitting, dropout and regularisation
    • Autoencoders and RBMs
  4. Unit 4: Computer Vision

    6 hours

    CNN layers, filters and parameter sharing; convolution and pooling; LeNet, AlexNet, VGG and DenseNet; weight initialisation and hyperparameter tuning; ResNet.

    Marks: 17–18 in the end-semester exam

    • Convolution and pooling
    • CNN architectures: LeNet, AlexNet and VGG
    • ResNet and DenseNet
    • Training CNNs
  5. Unit 5: Natural Language Processing

    6 hours

    RNNs and bidirectional RNNs; encoder–decoder sequence models; BPTT; LSTM and GRU; introduction to GANs.

    Marks: 17–18 in the end-semester exam

    • Recurrent neural networks
    • LSTM and GRU
    • Sequence-to-sequence models
    • Generative adversarial networks
  6. Unit 6: Case Studies and Applications

    6 hours

    Image classification and detection with ImageNet models; WaveNet for audio; sentiment analysis, text preprocessing and chatbots.

    Marks: 17–18 in the end-semester exam

    • Image classification and detection
    • Sentiment analysis and chatbots

Unit contents are summarised from the official SPPU syllabus . AiCanCode.org is not affiliated with Savitribai Phule Pune University.