AI & Deep Learning with TensorFlow Training

AI & Deep learning with Tensorflow course Training aims to impart training on the essentials of the Tensorflow and throws light on the aspects such as: main functions, operations and the execution pipeline. The candidates will gain complete understanding on the types of the Deep Architectures, such as Convolutional Networks and Recurrent Networks. The candidates will get to learn about the deep neural networks and its uses in complex raw data using TensorFlow.

After completing the AI & Deep learning with Tensorflow course, the candidates would be able to:

• Understand the Autoencoders and varitional Autoencoders
• Learn to apply the Analytical mathematics to the data
• Understand what Neural networks are?
• Learn about Autoencoders and discuss their Applications
• Learn about the application of Convolutional Neural Networks
• Develop understanding of Unsupervised Learning
• Learn how to run a “Hello World” program in TensorFlow
• Describe Deep Learning
• Learn about TFlearn implementation
• Learn the implementation procedure of Collaborative Filtering with RBM
• Understand what Restricted Boltzmann Machine is?
• Learn about Autoencoders and discuss their Applications

Target audience

• The Developers aspiring to be a 'Data Scientist'
• The Business Analysts willing to understand Deep Learning (ML) Techniques
• The Analytics Managers willing to lead the team of analysts
• The Information Architects willing to gain expertise in Predictive Analytics
• Analysts wanting to understand Data Science methodologies
• The Professionals willing to captivate and analyze Big Data

Prerequisites

Basic mathematical Knowledge is required for this training.

1 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
• The Math behind Machine Learning: Linear Algebra
  • Scalars
  • Vectors
  • Matrices
  • Tensors
  • Hyperplanes
• The Math Behind Machine Learning: Statistics
  • Probability
  • Conditional Probabilities
  • Posterior Probability
  • Distributions
  • Samples vs Population
  • Resampling Methods
  • Selection Bias
  • Likelihood
• Review of Machine Learning
  • Regression
  • Classification
  • Clustering
  • Reinforcement Learning
  • Underfitting and Overfitting
  • Optimization

2. Understanding the Fundamentals of Neural Networks Using 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

3. Deep Dive into Neural Networks 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

4. Master Deep Networks

• Why Deep Learning?
• SONAR Dataset Classification
• What is Deep Learning?
• Feature Extraction
• Working of a Deep Network
• Training using Backpropagation
• Variants of Gradient Descent
• Types of Deep Networks

5. Convolution Neural Networks (CNN)

• Introduction to CNNs
• CNNs Application
• Architecture of a CNN
• Convolution and Pooling layers in a CNN
• Understanding and Visualizing a CNN
• Transfer Learning and Fine-tuning Convolutional Neural Networks

6. Recurrent Neural Networks (RNN)

• Intro 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

7. Restricted Boltzmann Machine (RBM) & Autoencoders

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

8. Keras

• 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

9. TFlearn

• 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