Home > Store

Deep Learning with TensorFlow LiveLessons: Applications of Deep Neural Networks to Machine Learning Tasks

Deep Learning with TensorFlow LiveLessons: Applications of Deep Neural Networks to Machine Learning Tasks

Your browser doesn't support playback of this video. Please download the file to view it.

Online Video

Register your product to gain access to bonus material or receive a coupon.

Description

  • Copyright 2018
  • Edition: 1st
  • Online Video
  • ISBN-10: 0-13-477085-4
  • ISBN-13: 978-0-13-477085-7

6+ Hours of Video Instruction

Deep Learning with TensorFlow LiveLessons is an introduction to Deep Learning that bring the revolutionary machine-learning approach to life with interactive demos from the most popular Deep Learning library, TensorFlow, and its high-level API, Keras. Essential theory is whiteboarded to provide an intuitive understanding of Deep Learning’s underlying foundations, i.e., artificial neural networks. Paired with tips for overcoming common pitfalls and hands-on code run-throughs provided in Python-based Jupyter notebooks, this foundational knowledge empowers individuals with no previous understanding of neural networks to build powerful state-of-the-art Deep Learning models.


Skill Level

  • Intermediate


Learn How To

  • Build Deep Learning models in TensorFlow and Keras
  • Interpret the results of Deep Learning models
  • Troubleshoot and improve Deep Learning models
  • Understand the language and fundamentals of artificial neural networks
  • Build your own Deep Learning project

Who Should Take This Course

This course is perfectly suited to software engineers, data scientists, analysts, and statisticians with an interest in Deep Learning. Code examples are provided in Python, so familiarity with it or another object-oriented programming language would be helpful. Previous experience with statistics or machine learning is not necessary.


Course Requirements

Some experience with any of the following are an asset, but none are essential:

  • Object-oriented programming, specifically Python
  • Simple shell commands, e.g., in Bash
  • Machine learning or statistics
  • First-year college calculus


Lesson Descriptions

Lesson 1:  Introduction to Deep Learning

The first lesson starts off by giving the viewer an overview of deep learning, its roots in artificial neural networks, and the breadth of transformative applications it produces. Jon also goes over how to run the code examples provided throughout the LiveLessons, and then he builds an introductory neural network with you.

Lesson 2: How Deep Learning Works

The lesson begins with a discussion of the main families of deep neural networks and their applications. The heart of the lesson is a high-level overview of the essential theory that underlies deep learning. To bring this theory to life, Jon shows you deep learning in action via a web application called the TensorFlow Playground. He introduces the archetypal deep learning data sets, and then you build a deep neural network together to tackle a classic machine vision problem.

Lesson 3: Convolutional Networks

The previous lesson covered the principal foundations of deep learning and enabled you to construct a deep network. This lesson builds upon those theoretical foundations to build more effective deep nets. You immediately take that effectiveness a big step further by gaining an understanding of convolutional layers and how they have can be stacked to solve increasingly complex problems with larger data sets. In order to make sense of the outputs from these sophisticated models, the TensorBoard result-visualization tool is added to your arsenal at the end of the lesson.

Lesson 4: Introduction to TensorFlow

Up to this point you use the high-level deep learning API Keras to build your models. In this lesson, the leading Deep Learning libraries are compared, and then you get down to business with TensorFlow, the open-source library doing the heavy neural network-lifting underneath Keras and, in Jon’s opinion, clearly the best choice from the options available. Given this, the second half of the lesson is dedicated to building your own deep learning models in TensorFlow.

Lesson 5: Improving Deep Networks

In Lesson 5 you delve deeper into TensorFlow, leveraging it to improve the performance of your deep learning models, including by tuning model hyperparameters. The lesson concludes by discussing how to build your own deep learning project as well as outlining resources for further self-study.

About the Instructor

Jon Krohn is the chief data scientist at untapt, a machine learning startup in New York. He leads a Deep Learning Study Group and, having obtained his doctorate in neuroscience from Oxford University, continues to publish academic papers.


About Pearson Video Training

Pearson publishes expert-led video tutorials covering a wide selection of technology topics designed to teach you the skills you need to succeed. These professional and personal technology videos feature world-leading author instructors published by your trusted technology brands: Addison-Wesley, Cisco Press, Pearson IT Certification, Prentice Hall, Sams, and Que. Topics include: IT Certification, Network Security, Cisco Technology, Programming, Web Development, Mobile Development, and more.  Learn more about Pearson Video training at  http://www.informit.com/video.

Sample Content

Table of Contents

Introduction to Deep Learning with TensorFlow LiveLessons

Lesson 1: Introduction to Deep Learning

Topics

1.1 Neural Networks and Deep Learning

1.2 Running the Code in These LiveLessons

1.3 An Introductory Artificial Neural Network

Lesson 2: How Deep Learning Works

Topics

2.1 The Families of Deep Neural Nets and their Applications

2.2 Essential Theory I—Neural Units, Cost Functions, Gradient Descent, and Backpropagation

2.3 Essential Theory II—Cost Functions, Gradient Descent, and Backpropagation

2.4 TensorFlow Playground—Visualizing a Deep Net in Action

2.5 Data Sets for Deep Learning

2.6 Applying Deep Net Theory to Code I

Lesson 3: Convolutional Networks

Topics

3.1 Essential Theory III—Mini-Batches, Unstable Gradients, and Avoiding Overfitting

3.2 Applying Deep Net Theory to Code II

3.3 Introduction to Convolutional Neural Networks for Visual Recognition

3.4 Classic ConvNet Architectures—LeNet-5

3.5 Classic ConvNet Architectures—AlexNet and VGGNet

3.6 TensorBoard and the Interpretation of Model Outputs

Lessons 4: Introduction to TensorFlow

Topics

4.1 Comparison of the Leading Deep Learning Libraries

4.2 Introduction to TensorFlow

4.3 Fitting Models in TensorFlow

4.4 Dense Nets in TensorFlow

4.5 Deep Convolutional Nets in TensorFlow

Lesson 5: Improving Deep Networks

Topics

5.1 Improving Performance and Tuning Hyperparameters

5.2 How to Build Your Own Deep Learning Project

5.3 Resources for Self-Study

Summary of Deep Learning with TensorFlow LiveLessons

Updates

Submit Errata

More Information

Unlimited one-month access with your purchase
Free Safari Membership