Indian Institute of Information Technology, Allahabad

Department of Information Technology

Course Syllabus for Deep Learning

  1. Name of the Course: Deep Learning
  2. LTP structure of the course: 2-1-1
  3. Objective of the course: To get the students and researchers exposed to the state of the art deep learning techniques, approaches and how to optimize their results to increase its efficiency and get some hands-on on the same to digest the important concepts.
  4. Outcome of the course: As deep learning has demonstrated its tremendous ability to solve the learning and recognition problems related to the real world problems, the software industries have accepted it as an effective tool. As a result there is a paradigm shift of learning and recognition process. The students and researchers should acquire knowledge about this important area and must learn how to approach to a problem, whether to deal with deep learning solution or not. After undergoing this course they should be able to categorize which algorithm to use for solving which kind of problem. Students will be able to find out the ways to regularize the solution better and optimize it as per the problem requirement. Students will be exposed to the background mathematics involved in deep learning solutions. They will be able to deal with real time problems and problems being worked upon in industries. Taking this course will substantially improve their acceptability to the machine learning community – both as an intelligent software developer as well as a matured researcher.
  5. Course Plan:

Component

Unit

Topics for Coverage  

Component 1

Unit 1

Basic concepts of perceptron, learning and recognition- supervise and unsupervised learning. Fundamentals of delta learning rules and back propagation algorithm, SVM, KNN. Machine Learning, machine learning techniques, challenges motivating deep learning. over fitting and under fitting, bias and variance, Gradient based optimization, Maximum LikelihoodEstimation. Deep Feed-forward network, backpropagation. Some Regularization and Optimization Techniques

Unit 2

Convolutional Neural Network, RNN, methodology and Applications of deep learning

Component 2

Unit 3

Linear Factor Models and Autoencoders

Monte Carlo Methods, Stochastic Maximum, Likelihood and Contrastive Divergence

Unit 4

Deep Generative Models: Boltzmann Machine, RBM, Deep Belief Nets, Deep Boltzmann Machine, Convolutional Boltzmann Machine

6. Text Book:

Deep Learning by- Ian Goodfellow, Yoshua Bengio and Aaron Courville

In addition other machine learning books , research papers etc. will be used.