SPPU BE IT syllabus

SPPU · Final Year Information Technology · 2019 Course

Deep Learning

414443 · Semester VII · 3 credits · In-semester 30 + end-semester 70

All notes for this subject
  1. Unit 1: Fundamentals of Deep Learning

    6 hours

    Multilayer perceptrons; feed-forward networks and backpropagation; gradient descent; vanishing gradients; ReLU variants; optimisers; hyperparameters: layer size, momentum and learning rate; dropout, DropConnect, L1 and L2.

    Marks: 15 in the in-semester exam

    • Multilayer perceptron and backpropagation
    • Gradient descent and optimisers
    • Vanishing gradient problem
    • Activation functions
    • Regularisation: dropout, L1 and L2
  2. Unit 2: Convolutional Neural Networks

    6 hours

    Convolution; parameter sharing and equivariance; pooling; convolution variants; basic CNN architecture; AlexNet.

    Marks: 15 in the in-semester exam

    • Convolution and parameter sharing
    • Pooling
    • CNN architecture
    • AlexNet
  3. Unit 3: Recurrent Neural Networks

    6 hours

    Types of RNNs; feed-forward versus recurrent networks; LSTMs; encoder–decoder architectures; recursive neural networks.

    Marks: 17–18 in the end-semester exam

    • Recurrent neural networks
    • LSTM networks
    • Encoder-decoder architectures
    • Recursive neural networks
  4. Unit 4: Autoencoders

    6 hours

    Undercomplete, sparse, denoising and contractive autoencoders; stochastic encoders and decoders; applications.

    Marks: 17–18 in the end-semester exam

    • Undercomplete autoencoders
    • Sparse and denoising autoencoders
    • Contractive autoencoders
    • Applications of autoencoders
  5. Unit 5: Representation Learning

    6 hours

    Greedy layer-wise pre-training; transfer learning and domain adaptation; distributed representations; DenseNet.

    Marks: 17–18 in the end-semester exam

    • Greedy layer-wise pre-training
    • Transfer learning and domain adaptation
    • DenseNet
  6. Unit 6: Applications

    6 hours

    Image classification; social network analysis; speech recognition; recommender systems; NLP.

    Marks: 17–18 in the end-semester exam

    • Deep learning for image classification
    • Deep learning for speech and NLP
    • Deep learning recommender systems

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