Unit 1 UNIT-I

2 lecture hours

• Introduction: AI, ML and DL, Research Domain and industry applications
• Tools and technologies
• Perspective of deep learning

Unit 2 UNIT-II

6 lecture hours

• Fundamental of Neural Network: Introduction
• Understanding the biological neuron
• Exploring the artificial neuron
• Early implementation of ANN, Types of activation functions
• Architectures of neural network
• Learning process in ANN

Unit 3 UNIT- III

10 lecture hours

• Training Deep Neural Network: Introduction
• Mathematics behind backpropagation
• Deep L layer neural network
• Understanding of notion of forward and backward propagation in perspective of computation graph
• Initializing weights in neural network
• Mini batch and stochastic gradient descent
• Other optimization algorithms
• Normalization of inputs

Unit 4 UNIT-IV

10 lecture hours

• Computer Vision using Convolutional Neural Network w.e.f
• AY 2021-22 Introduction to computer vision
• Challenges faced by traditional ANN to work with image data
• Building blocks of convolutional neural network
• Building a convolutional neural network
• CNN architecture

Unit 5 UNIT- V

6 lecture hours

• Representation Learning: Introduction
• Autoencoder fundamentals
• Regularization of autoencoder
• Representation learning in text
• Traditional methods
• Word embedding
• Document embedding

Unit 6 UNIT-VI

4 lecture hours

• Sequence Based Models: Introduction to sequence data
• Recurrent neural network
• Long short term memory
• Gated recurrent units
• Bi-directional models
• Language modelling and sequence modelling

Unit 7 UNIT-VII

• Deep Learning Case Studies: Disease detection from chest X ray images
• Colorization of grayscale images
• Obtain vector representation from source code
• Recent Development in Deep Learning (Study from latest research papers from Scopus indexed/web of science journals