Deep Learning Course Outline

Course Outline: Introduction to Deep Learning

  • Understand the main fundamentals that drive Deep Learning
  • Be able to build, train and apply fully connected deep neural networks
  • Know how to implement efficient CNN or RNN.
  • Understand the key features in a neural network’s architecture
    .

Course Description

This course aims to present the core fundamentals behind the much talked about field of Deep Learning. We will delve into selected topics of Deep Learning, from discussing basics of neural networks, to understanding how CNN and RNN works with common examples and publicly available datasets. Special highlight of the course is the lecture on Interpretability of Neural Networks which will help students to understand how to trust a neural network’s recommendation. In the final weeks of the course, we shall get an introductory exposure to Generative Adversarial Networks and Reinforcement Learning which will help build the foundation for more advanced courses in Artificial Intelligence.

Duration

  • Self Paced Learning: 30-40 hours
  • Instructor Led Sessions: 12 hours

Outline

Module 1 Fundamentals of Deep Learning

  • What is Deep Learning
  • Applications
  • Weights and Activation functions
  • Perceptron
  • Data Preprocessing
  • Image augmentation in OpenCV

Module 2 Neural Networks

  • Neural Networks
  • Applications
  • Loss function
  • Backpropagation
  • MNIST example for Neural Networks

Module 3 Convolutional Neural Networks (CNN)

  • What are convolutional neural network and tensorflow
  • Convolutional layer
  • Pooling layer
  • How to create the layers in Python

Module 4 Convolutional Neural Networks (CNN)

  • Convolutional neural network with Python
  • Transfer learning
  • RCNN (Fast RCNN, Faster RCNN, Mask RCNN)

Module 5 Representation learning and Generative learning

  • Auto encoder
  • Generative adversarial Networks
  • Simple example with MNIST dataset
  • Limitation of GAN and Deep Convolutional GANs

Module 6 Deep Learning applications for Reinforcement Learning and NLP

  • Key elements of Reinforcement Learning
  • OpenAI Gym Toolkit
  • How is Deep Learning applied to RL
  • Robotic Manipulation using Deep RL
  • Application of Deep learning to Natural Language Processing
  • Automatic Language Translation
  • Automatic Text Classification

Note: Practice Jupyter Notebook shall be provided for practice with each module