RTMNU Final AI & ML syllabus

RTMNU · Final Year B.Tech Artificial Intelligence & Machine Learning · CBCS

Deep Learning

BTAI&ML701T · Semester VII · 3 credits · College 30 + university 70

Unit 4's applications are a deep CNN for Telugu OCR and LSTMs for text processing.

  1. Unit 1: Mathematical Preliminaries and Machine Learning Basics

    Linear algebra, principal component analysis, probability and statistics, numerical methods and gradient- and constraint-based optimisation; learning algorithms — training, validation and test sets; neural, convolutional and recurrent networks and backpropagation; performance metrics, hyperparameters and debugging.

    Examined in the 70-mark end-semester paper

    • Vectors and matrices for data science
    • Eigen-decomposition, PCA and SVD
    • Probability and Bayes' theorem
    • Gradient descent variants
    • Cross-validation and model evaluation
    • Hyperparameters in deep learning
    • Debugging strategies for deep networks
  2. Unit 2: Introduction to Deep Networks

    Problems with backpropagation and modern approaches; autoencoders and representation learning; regularisation, dropout and optimisation strategies.

    Examined in the 70-mark end-semester paper

    • Backpropagation
    • Vanishing and exploding gradients
    • Autoencoders and VAEs
    • Representation learning
    • Regularisation and dropout
    • Optimisers: AdaGrad, RMSProp and Adam
  3. Unit 3: Sequence Learning and LSTMs

    Deep recurrent and bidirectional networks and encoder–decoder architectures; the LSTM and building an LSTM network.

    Examined in the 70-mark end-semester paper

    • Recurrent neural networks
    • Bidirectional and deep RNNs
    • Encoder-decoder sequence models
    • LSTM
  4. Unit 4: Applications

    A deep convolutional network for Telugu OCR and its performance; LSTM networks for text processing.

    Examined in the 70-mark end-semester paper

    • Optical character recognition with deep CNNs
    • LSTMs and GRUs for language
  5. Unit 5: GANs and Latest Advances

    Generative adversarial networks — building and training GANs, GAN variants and current results; the limitations and weaknesses of deep learning.

    Examined in the 70-mark end-semester paper

    • Generative adversarial networks
    • Types of GANs
    • Limitations of deep learning

Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).