Machine Learning Projects with TensorFlow 2.0

Video description

Build and train models for real-world machine learning projects using Tensorflow 2.0

About This Video

  • Make use of the amazing new feature of TensorFlow 2 called 'Eager Execution' which makes it easier to learn and use
  • Upgrade your skills by building real-world Machine Learning projects
  • Build, test and deploy different ML models and learn more modern techniques such as Reinforcement Learning and Transfer Learning

In Detail

TensorFlow is the world's most widely adopted framework for Machine Learning and Deep Learning. TensorFlow 2.0 is a major milestone due to its inclusion of some major changes making TensorFlow easier to learn and use such as "Eager Execution". It will support more platforms and languages, improved compatibility and remove deprecated APIs.

This course will guide you to upgrade your skills in Machine Learning by practically applying them by building real-world Machine Learning projects.

Each section should cover a specific project on a Machine Learning task and you will learn how to implement it into your system using TensorFlow 2. You will implement various Machine Learning techniques and algorithms using the TensorFlow 2 library. Each project will put your skills to test, help you understand and overcome the challenges you can face in a real-world scenario and provide some tips and tricks to help you become more efficient. Throughout the course, you will cover the new features of TensorFlow 2 such as Eager Execution. You will cover at least 3-4 projects. You will also cover some tasks such as Reinforcement Learning and Transfer Learning.

By the end of the course, you will be confident to build your own Machine Learning Systems with TensorFlow 2 and will be able to add this valuable skill to your CV.

Publisher resources

Download Example Code

Table of contents

  1. Chapter 1 : Regression Task Airbnb Prices in New York
    1. Course Overview 00:06:15
    2. Setting Up TensorFlow 2.0 00:03:17
    3. Getting Started with TensorFlow 2.0 00:08:55
    4. Analyzing the Airbnb Dataset and Making a Plan 00:03:50
    5. Implementing a Simple Linear Regression Algorithm 00:13:04
    6. Implementing a Multi Layer Perceptron (Artificial Neural Network) 00:11:38
    7. Improving the Network with Better Activation Functions and Dropout 00:05:42
    8. Adding More Metrics to Gain a Better Understanding 00:05:10
    9. Putting It All Together in a Professional Way 00:07:09
  2. Chapter 2 : Classification Task Build Real World Apps: Who Will Win the Next UFC?
    1. Collecting Possible Kaggle Data 00:04:08
    2. Analysis and Planning of the Dataset 00:05:03
    3. Introduction to Google Colab and How It Benefits Us 00:09:28
    4. Setting Up Training on Google Colab 00:09:56
    5. Some Advanced Neural Network Approaches 00:15:46
    6. Introducing a Deeper Network 00:05:31
    7. Inspecting Metrics with TensorBoard 00:09:56
    8. Inspecting the Existing Kaggle Solutions 00:03:07
  3. Chapter 3 : Natural Language Processing Task: How to Generate Our Own Text
    1. Introduction to Natural Language Processing 00:02:22
    2. NLP and the Importance of Data Preprocessing 00:07:42
    3. A Simple Text Classifier 00:06:44
    4. Text Generation Methods 00:01:36
    5. Text Generation with a Recurrent Neural Network 00:13:45
    6. Refinements with Federated Learning 00:08:59
  4. Chapter 4 : Reinforcement Learning Task: How to Become Best at Pacman
    1. Introduction to Reinforcement Learning 00:02:55
    2. OpenAI Gym Environments 00:09:32
    3. The Pacman Gym Environment That We Are Going to Use 00:06:07
    4. Reinforcement Learning Principles with TF-Agents 00:01:48
    5. TF-Agents for Our Pacman Gym Environment 00:12:49
    6. The Agents That We Are Going to Use 00:02:30
    7. Selecting the Best Approaches and Real World Applications 00:10:39
  5. Chapter 5 : Transfer Learning Task: How to Build a Powerful Image Classifier
    1. Introduction to Transfer Learning in TensorFlow 2 00:02:28
    2. Picking a Kaggle Dataset to Work On 00:11:40
    3. Picking a Base Model Suitable for Transfer Learning with Our Dataset 00:08:05
    4. Implementing our Transfer Learning approach 00:07:24
    5. How Well Are We Doing and Can We Do Better 00:13:45
    6. Conclusions and Future Work 00:01:43

Product information

  • Title: Machine Learning Projects with TensorFlow 2.0
  • Author(s): Vlad Sebastian Ionescu
  • Release date: April 2020
  • Publisher(s): Packt Publishing
  • ISBN: 9781838980252