AI & Deep Learning with TensorFlow

Learning Objectives:

In this module, you’ll get an introduction to Deep Learning and understand how Deep Learning solves problems which Machine Learning cannot. Understand fundamentals of Machine Learning and relevant topics of Linear Algebra and Statistics.

 Topics:

• Deep Learning: A revolution in Artificial Intelligence
• Limitations of Machine Learning
• What is Deep Learning?
• Advantage of Deep Learning over Machine learning
• 3 Reasons to go for Deep Learning
• Real-Life use cases of Deep Learning
• Review of Machine Learning: Regression, Classification, Clustering, Reinforcement Learning, Underfitting and Overfitting, Optimization

Hands-On

• Implementing a Linear Regression model for predicting house prices from Boston dataset
• Implementing a Logistic Regression model for classifying Customers based on a Automobile purchase dataset

Learning Objectives:

In this module, you’ll get an introduction to Neural Networks and understand it’s working i.e. how it is trained, what are the various parameters considered for its training and the activation functions that are applied.

Topics:

• How Deep Learning Works?
• Activation Functions
• Illustrate Perceptron
• Training a Perceptron
• Important Parameters of Perceptron
• What is TensorFlow?
• TensorFlow code-basics
• Graph Visualization
• Constants, Placeholders, Variables
• Creating a Model
• Step by Step - Use-Case Implementation

Hands-On

• Building a single perceptron for classification on SONAR dataset

Learning Objectives:

In this module, you’ll understand backpropagation algorithm which is used for training Deep Networks. You will know how Deep Learning uses neural network and backpropagation to solve the problems that Machine Learning cannot.

Topics:

• Understand limitations of a Single Perceptron
• Understand Neural Networks in Detail
• Illustrate Multi-Layer Perceptron
• Backpropagation – Learning Algorithm
• Understand Backpropagation – Using Neural Network Example
• MLP Digit-Classifier using TensorFlow
• TensorBoard

Hands-On

• Building a multi-layered perceptron for classification of Hand-written digits

Learning Objectives:

In this module, you’ll get started with the TensorFlow framework. You will understand how it works, its various data types & functionalities. In addition, you will create an image classification model

Topics:

• Why Deep Networks
• Why Deep Networks give better accuracy?
• Use-Case Implementation on SONAR dataset
• Understand How Deep Network Works?
• How Backpropagation Works?
• Illustrate Forward pass, Backward pass
• Different variants of Gradient Descent
• Types of Deep Networks

Hands-On

• Building a multi-layered perceptron for classification on SONAR dataset

Learning Objectives:In this module, you’ll understand convolutional neural networks and its applications. You will learn the working of CNN, and create a CNN model to solve a problem.

 Topics:

• Introduction to CNNs
• CNNs Application
• Architecture of a CNN
• Convolution and Pooling layers in a CNN
• Understanding and Visualizing a CNN

Hands-On

Building a convolutional neural network for image classification. The model should predict the difference between 10 categories of images.

Learning Objectives:

In this module, you’ll understand Recurrent Neural Networks and its applications. You will understand the working of RNN, how LSTM are used in RNN, what is Recursive Neural Tensor Network Theory, and finally you will learn to create a RNN model.

Topics:

• Introduction to RNN Model
• Application use cases of RNN
• Modelling sequences
• Training RNNs with Backpropagation
• Long Short-Term memory (LSTM)
• Recursive Neural Tensor Network Theory
• Recurrent Neural Network Model

Hands-On

• Building a recurrent neural network for SPAM prediction.

Learning Objectives:

In this module, you’ll understand RBM & Autoencoders along with their applications. You will understand the working of RBM & Autoencoders, illustrate Collaborative Filtering using RBM and understand what are Deep Belief Networks.

Topics:

• Restricted Boltzmann Machine
• Applications of RBM
• Collaborative Filtering with RBM
• Introduction to Autoencoders
• Autoencoders applications
• Understanding Autoencoders

Hands-On

• Building a Autoencoder model for classification of handwritten images extracted from the MNIST Dataset

Learning Objectives:

In this module, you’ll understand how to use Keras API for implementing Neural Networks. The goal is to understand various functions and features that Keras provides to make the task of neural network implementation easy.

Topics:

• Define Keras
• How to compose Models in Keras
• Sequential Composition
• Functional Composition
• Predefined Neural Network Layers
• What is Batch Normalization
• Saving and Loading a model with Keras
• Customizing the Training Process
• Using TensorBoard with Keras
• Use-Case Implementation with Keras

Hands-On

• Build a model using Keras to do sentiment analysis on twitter data reactions on GOP debate in Ohio

Learning Objectives:

In this module, you’ll understand how to use TFLearn API for implementing Neural Networks. The goal is to understand various functions and features that TFLearn provides to make the task of neural network implementation easy.

Topics:

• Define TFLearn
• Composing Models in TFLearn
• Sequential Composition
• Functional Composition
• Predefined Neural Network Layers
• What is Batch Normalization
• Saving and Loading a model with TFLearn
• Customizing the Training Process
• Using TensorBoard with TFLearn
• Use-Case Implementation with TFLearn

Hands-On

• Build a recurrent neural network using TFLearn to do image classification on hand-written digits

Learning Objectives:

In this module, you should learn how to approach and implement a project end to end. The instructor will share his industry experience and related insights that will help you kickstart your career in this domain. In addition, we will be having a QA and doubt clearing session for you.

Topics:

• How to approach a project? 
• Hands-On project implementation
• What Industry expects?
• Industry insights for the Machine Learning domain
• QA and Doubt Clearing Session