DBATU TY Computer syllabus

DBATU · Third Year B.Tech Computer Engineering · NEP 2020

Deep Learning

26AF1245PE605 · Elective III · Semester VI · 3 credits · Continuous assessment 20 + mid-semester 20 + end-semester 60

One of the Elective III options.

All notes for this subject
  1. Unit 1: Machine Learning Basics and Neural Networks

    6 hours

    Regression, kNN, probabilistic classifiers, decision trees, random forests and SVMs; the artificial neuron and perceptron; stochastic gradient descent and backpropagation; network architectures and hyperparameters.

    Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then

    • Deep learning vs machine learning
    • Perceptron and feed-forward networks
    • Forward and backpropagation
  2. Unit 2: Deep Architectures and Convolutional Networks

    6 hours

    Hyperparameters, loss, learning rate, momentum, regularisation, dropout and batch norm; vanishing gradients; from dense layers to convolutions and pooling; AlexNet to DenseNet; segmentation and object detection.

    Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then

    • Hyperparameters: learning rate, momentum and regularisation
    • Regularisation: dropout, batch normalisation and early stopping
    • Gradient descent and vanishing and exploding gradients
    • CNN architecture
    • Pooling and fully connected layers
    • CNN architectures: VGG, GoogLeNet, ResNet and DenseNet
    • Object detection and image segmentation
  3. Unit 3: Deep Sequence Models

    6 hours

    Sequence-modelling problems; RNNs and backpropagation through time; GRUs and LSTMs; deep RNNs; image captioning and video-to-text with LSTMs.

    Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then

    • Recurrent neural networks
    • Backpropagation through time
    • Long-term dependencies, LSTM and GRU
    • Bidirectional and deep RNNs
  4. Unit 4: Deep Unsupervised Learning and Transfer Learning

    6 hours

    Latent-variable models and autoencoders; variational autoencoders; GANs and image generation; transfer learning and data augmentation.

    Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then

    • Autoencoders
    • Variational autoencoders
    • Generative adversarial networks
    • Transfer learning and data augmentation
  5. Unit 5: Responsible AI, MLOps and Industrial Applications

    6 hours

    Explainable, fair and responsible AI; evaluation metrics; deployment strategies and MLOps; cloud deployment and monitoring; AI agents; case studies across industries.

    Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then

    • Explainable and responsible AI
    • MLOps and model deployment

Unit contents are summarised from the official DBATU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Technological University (DBATU).