About Erudition

Erudition is a leading e-learning platform providing live instructor-led interactive online training. We cater to professionals and students across the globe in categories like Big Data & Hadoop, Business Analytics, NoSQL Databases, Java & Mobile Technologies, System Engineering, Project Management and Programming. We have an easy and affordable learning solution that is accessible to millions of learners. With our students spread across countries like the US, India, UK, Canada, Singapore, Australia, Middle East, Brazil and many others, we have built a community of over 1 million learners across the globe.

About Course

In this Deep Learning in TensorFlow with Python Training we will learn about what is AI, explore neural networks, understand deep learning frameworks, implement various machine learning algorithms using Deep Networks. We will also explore how different layers in neural networks does data abstraction and feature extraction using Deep Learning. Edureka’s Deep Learning in TensorFlow training is designed to make you a Data Scientist by providing you rich hands-on training on Deep Learning in TensorFlow with Python. This course is a stepping stone in your Data Science journey using which you will get the opportunity to work on various Deep Learning projects.

Curriculum

Introduction to Deep Learning

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

Understanding Neural Networks with TensorFlow

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

Deep dive into Neural Networks with TensorFlow

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

Master Deep Networks

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

Convolutional Neural Networks (CNN)

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.

Recurrent Neural Networks (RNN)

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.

Restricted Boltzmann Machine (RBM) and Autoencoders

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

Keras API

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

TFLearn API

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

In-Class Project

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