Modern Deep Learning Techniques using TensorFlow Training

In this TensorFlow Deep Learning course, you will gain the skills and knowledge required to leverage TensorFlow to solve real-world Deep Learning problems. You will learn how to:

• Understand tensors and their variables
• Use TensorFlow's sequential and functional API

TensorFlow Deep Learning Training Delivery Methods

• In-Person

• Online

TensorFlow Deep Learning Training Benefits

• Leverage artificial neural networks

• Understand the strengths and limitations of TensorFlow

• Use TensorFlow 2.x, from fundamentals to building blocks
• Train, test, and evaluate a TensorFlow Model

• Deploy a trained TensorFlow Model

• Continue learning and face new challenges with after-course one-on-one instructor coaching

TensorFlow Deep Learning Training Outline

Module 1: Understanding Artificial Neural Networks and TensorFlow

In this module, you will learn:

• The basics of artificial neural networks
• The lifecycle of building a TensorFlow model
• The basics of Deep Learning
• Layered architecture of TensorFlow
• Constants, variables and Tensors

Lab:

• Introduction to Tensors and Variables

Module 2: Feature Engineering with TensorFlow

In this module, you will learn how to:

• Use tf.data
• Define a Keras Model
• Build wide and deep models

Lab:

• Exploring tf.data
• Using TensorFlow sequential API
• Using TensorFlow functional API

Module 3: TensorFlow Under the Hood

In this module, you will learn about:

• Defining gradient descent
• Activation functions
• Hyperparameters
• Regularisation

Lab:

• Keras and TensorFlow

Module 4: Feature Engineering

In this module, you will learn about:

• Basics of Feature Engineering
• Raw Data and Features
• Feature Crosses
• Transform

Lab:

• Feature Engineering
• Basic Feature Engineering in Keras
• Advanced Feature Engineering in Keras
• Exploring Tf.transform

Module 5: Monitoring and Deployment

In this module, you will learn about:

• Monitoring with TensorBoard
• Saving and Versioning Model
• Deploying Models

Lab:

• Using TensorBoard to Monitor the performance