Artificial Intelligence & Deep Learning with TensorFlow

Secure enrollment now


Introduction to Deep Learning

•    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


Understanding Neural Networks with TensorFlow

•    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

Deep dive into Neural Networks with TensorFlow

•    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

Master Deep Networks

•    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

Convolutional Neural Networks (CNN)

•    Introduction to CNNs

•    CNNs Application

•    Architecture of a CNN

•    Convolution and Pooling layers in a CNN

•    Understanding and Visualizing a CNN

Recurrent Neural Networks (RNN)

•    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

Restricted Boltzmann Machine (RBM) and Autoencoders

•    Restricted Boltzmann Machine

•    Applications of RBM

•    Collaborative Filtering with RBM

•    Introduction to Autoencoders

•    Autoencoders applications

•    Understanding Autoencoders

Keras API

•    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


•    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

In-Class Project

•    How to approach a project? 

•    Hands-On project implementation

•    What Industry expects?

•    Industry insights for the Machine Learning domain

•    QA and Doubt Clearing Session

Complimentary sessions on communication presentation and leadership skills.

Benefits from the course

Mode of Teaching

Live Interactive

  • AI, Machine Learning and Deep Learning fall under one Umbrella - Data Science.

  • AI is not future. It is rather near future and to keep up with the changing demand of the industry one ought to delve into Deep Learning.

  • It enables CS Engineers to stay in their career by mastering the huge paradigm shift the way Machine Learning is now being implemented to achieve Artificial Intelligence. This course is most suited for:

  • Object Oriented application developers who aspire to carve out their career in the field of Data Science.

  • Professionals having basic understanding of Data Science concepts.

  • Statistics and Probability professionals involved in Data Mining and Interpretation techniques.

  • Software professionals who already have Big Data background and aspire to delve into developing automated learning features of a system.


  • Basic programming knowledge in Python

  • Concepts about Machine Learning


  • Basic programming knowledge in Python
  • Concepts about Machine Learning

Course Duration:

30 Hours

Class Hours:

2 Hours Daytime slots or 3 Hours week end Slots (May change)

Video Clip