O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

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

Video Description

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.

The companion materials for this LiveLesson can be found at https://github.com/the-deep-learners/TensorFlow-LiveLessons/.

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

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.

Table of Contents

  1. Introduction
    1. Deep Learning with TensorFlow: Introduction 00:02:27
  2. Lesson 1: Introduction to Deep Learning
    1. Topics 00:00:31
    2. 1.1 Neural Networks and Deep Learning 00:15:05
    3. 1.2 Running the Code in These LiveLessons 00:08:54
    4. 1.3 An Introductory Artificial Neural Network 00:29:47
  3. Lesson 2: How Deep Learning Works
    1. Topics 00:00:40
    2. 2.1 The Families of Deep Neural Nets and their Applications 00:05:00
    3. 2.2 Essential Theory I—Neural Units 00:23:26
    4. 2.3 Essential Theory II—Cost Functions, Gradient Descent, and Backpropagation 00:15:39
    5. 2.4 TensorFlow Playground—Visualizing a Deep Net in Action 00:15:31
    6. 2.5 Data Sets for Deep Learning 00:06:05
    7. 2.6 Applying Deep Net Theory to Code I 00:15:10
  4. Lesson 3: Convolutional Networks
    1. Topics 00:00:48
    2. 3.1 Essential Theory III—Mini-Batches, Unstable Gradients, and Avoiding Overfitting 00:28:22
    3. 3.2 Applying Deep Net Theory to Code II 00:21:14
    4. 3.3 Introduction to Convolutional Neural Networks for Visual Recognition 00:05:57
    5. 3.4 Classic ConvNet Architectures—LeNet-5 00:15:43
    6. 3.5 Classic ConvNet Architectures—AlexNet and VGGNet 00:23:51
    7. 3.6 TensorBoard and the Interpretation of Model Outputs 00:13:39
  5. Lesson 4: Introduction to TensorFlow
    1. Topics 00:00:40
    2. 4.1 Comparison of the Leading Deep Learning Libraries 00:04:51
    3. 4.2 Introduction to TensorFlow 00:27:55
    4. 4.3 Fitting Models in TensorFlow 00:30:10
    5. 4.4 Dense Nets in TensorFlow 00:34:14
    6. 4.5 Deep Convolutional Nets in TensorFlow 00:28:57
  6. Lesson 5: Improving Deep Networks
    1. Topics 00:00:30
    2. 5.1 Improving Performance and Tuning Hyperparameters 00:11:49
    3. 5.2 How to Build Your Own Deep Learning Project 00:06:07
    4. 5.3 Resources for Self-Study 00:02:22
  7. Summary
    1. Deep Learning with TensorFlow: Summary 00:01:15