TensorFlow Certification Training

• Explain Deep learning
• Define the motivations behind the Deep Learning
• Describe Neural networks
• Train the Neural networks
• Discuss Backpropagation
• Define Variational Autoencoders and Autoencoders
• Run “Hello World” program in the TensorFlow
• Define Convolutional Neural Networks
• Discuss the RNN
• Explain the theory of Recursive Neural Tensor Network
• Execute the model of Recursive Neural Network
• Explain Unsupervised Learning
• Discuss the various applications of Unsupervised Learning
• Describe the Restricted Boltzmann Machine

• Application Developers
• Data Analysts
• Data Scientists
• Professionals with basic knowledge of Machine Learning and Programming
• Academic Researchers

• Candidates must have basic knowledge of Programming mainly in the C++ or Python.
• Having knowledge of Arrays Concepts would be an added advantage.
• A clear understanding of the Machine Learning Concepts is compulsory.

1. An Introduction to Deep Learning

• An overview of Deep Learning
• Deep Learning- A massive change in the Artificial Intelligence
• An overview of Machine Learning
• Limitations of Machine Learning
• Reasons to go with Deep Learning over Machine Learning

2. Understanding Fundamentals of Neural Networks using TensorFlow

• Work process of Deep Learning
• Different Activation Functions
• How Deep Learning Works?
• Activation Functions
• A Brief of Perceptron
• Training a Perceptron
• Key Parameters of Perceptron
• An explanation of Tensorflow?
• TensorFlow and its code-basics
• Graph Visualization
• Constants, Placeholders, Variables
• Creating a Model
• Step-by-Step process of Use-Case Implementation

3. Explanation of the Neural Networks using TensorFlow

• An overview of the limitations of a single Perceptron
• Knowing the limitations of A Single Perceptron
• Know Neural Networks in-depth
• Explanation of Multi-layer Perceptron
• Backpropagation- Learning Algorithm
• An overview of Backpropagation- Using Neural Network with Examples
• MLP Digit-Classifier using TensorFlow
• TensorBoard
• Summary

4. Master Deep Networks

• Why go to the Deep Learning? 
• Classification of the SONAR Dataset 
• What is Deep Learning? 
• Extraction of the Features
• Work process of the Deep Network 
• Training using Backpropagation 
• Options of Gradient Descent 
• Different Types of Deep Networks

5. Convolutional Neural Networks (CNN)

• An introduction to Convolutional Neural Networks
• Applications of the Convolutional Neural Networks
• Architecture of Convolutional Neural Networks
• Pooling and Convolutional layers in the Convolutional Neural Networks
• Visualizing the Convolutional Neural Networks
• Fine-tuning and transfer learning Convolutional Neural Networks

6. Recurrent Neural Networks (RNN)

• An introduction to Recurrent Neural Networks
• Applying use cases of Recurrent Neural Networks
• Modelling sequences of Recurrent Neural Networks
• Training RNNs with Backpropagation 
• Long and short-term memory (LSTM)
• Theory of Neural Tensor Network
• Different Models of Recurrent Neural Network

7. Restricted Boltzmann Machine (RBM) and Autoencoders

• An overview of Restricted Boltzmann Machine
• Different applications of RBM
• Combined Filtering with RBM
• An overview of Autoencoders
• Applications of Autoencoders
• Understanding of Autoencoders

8. An Introduction to Keras

• An overview of Keras
• Ways to create models in Keras
• Functional and Sequential Compositions
• Predefined Neural Network Layers
• Batch Normalization: What exactly it is?
• Saving and loading the models with Keras
• Customization of the training process
• Uses of TensorBoard with Keras
• Process of Use-Case Implementation with Keras

9. An Introduction to TFlearn

• An overview of TFlearn
• Composing models in TFlearn
• Functional and Sequential Compositions
• Predefined Neural Network Layers
• Batch Normalization: What exactly it is?
• Saving and loading the models with TFlearn
• Customization of the training process
• Uses of TensorBoard with TFlearn
• Process of Use-Case Implementation with TFlearn