O'Reilly logo
live online training icon Live Online training

Introduction to Deep Learning (with TensorFlow 2.0): Complete Artificial Intelligence Series

A Hands-On Primer on State-of-the-Art Deep Neural Networks

Jon Krohn

Relatively obscure a few short years ago, Deep Learning is ubiquitous today across data-driven applications as diverse as machine vision, natural language processing, and super-human game-playing.

This Deep Learning primer brings the revolutionary approach behind contemporary artificial intelligence to life with interactive demos featuring TensorFlow 2.0, the brand-new, major update of the most popular Deep Learning library.

To facilitate an intuitive understanding of Deep Learning’s artificial-neural-network foundations, essential theory will be introduced visually and pragmatically. Paired with tips for overcoming common pitfalls and hands-on code run-throughs provided in straightforward Jupyter notebooks, this foundational knowledge empowers you to build powerful state-of-the-art Deep Neural Network models.

This is part of Jon Krohn’s Complete Artificial Intelligence Series, a collection of interactive trainings that together comprehensively cover the foundations of modern AI approaches. The recommended progression through the Series is to take one of these two introductory sessions:

Following either of the introductory sessions (or if you’re familiar with the content covered in Chapters 1 and 5-9 of Jon Krohn’s Deep Learning Illustrated book), you’re well-prepared to specialize in any of the other Live Trainings in the Complete Artificial Intelligence Series, which can be undertaken in any order you fancy:

What you'll learn-and how you can apply it

  • Understand the essential theory of of artificial neural networks
  • Build production-ready Deep Neural Networks in TensorFlow 2.0 by taking advantage of its in-built, easy-to-use Keras module
  • Interpret the output of Deep Learning models to troubleshoot and improve results

This training course is for you because...

  • You work with data and want to be exposed to the range of applications of Deep Learning approaches.
  • You want to understand how Deep Learning works.
  • You want to create state-of-the-art machine-learning models well-suited to solving a broad range of problems, including complex, non-linear problems with large, high-dimensional data sets.

Prerequisites

  • Experience with an object-oriented programming language, e.g., Python (all code demos during the training will be in Python)
  • Some experience with machine learning would make this Live Training easier to follow, but is by no means necessary

Materials, downloads, or Supplemental Content needed in advance:

  • During class, we’ll work on Colab notebooks interactively in the cloud. This requires nearly zero setup and instructions will be provided in class. If you’d like to take a sneak peak at the notebooks we’ll be using, check out http://github.com/jonkrohn/tf2

Resources

About your instructor

  • Jon Krohn is Chief Data Scientist at the machine learning company untapt. He is the presenter of a popular series of tutorials on artificial neural networks, including Deep Learning with TensorFlow, and is the author of Deep Learning Illustrated, the acclaimed book released by Pearson in 2019. Jon holds a doctorate in neuroscience from Oxford University and has been publishing on machine learning in leading academic journals since 2010. He teaches his deep learning curriculum at the NYC Data Science Academy as well as Columbia University. Along with researchers at Columbia’s medical center, Dr. Krohn holds a National Institutes of Health grant to automate medical image processing with deep learning.

Schedule

The timeframes are only estimates and may vary according to how the class is progressing

Segment 1: The Unreasonable Effectiveness of Deep Learning (45 min)

  • Training Overview
  • A Brief History of the Rise of Deep Learning
  • Deep Learning vs Other Machine Learning Approaches
  • Dense Feedforward Networks
  • Convolutional Networks for Machine Vision
  • Recurrent Networks for Natural Language Processing and Time-Series Predictions
  • Deep Reinforcement Learning for Sequential Decision-Making
  • Generative Adversarial Networks for Creativity
  • Overview of the Leading Deep Learning Libraries, including TensorFlow 2.0, Keras, PyTorch, MXNet, CNTK, and Caffe

Segment 2: Essential Deep Learning Theory (75 min)

  • Hands-on Jupyter Notebook Demo: An Artificial Neural Network in TensorFlow 2.0
  • The Essential Math of Artificial Neurons
  • The Essential Math of Neural Networks
  • Activation Functions
  • Cost Functions, including Cross-Entropy
  • Stochastic Gradient Descent
  • Backpropagation
  • Mini-Batches
  • Learning Rate
  • Fancy Optimizers (e.g., Adam, Nadam)
  • Glorot/He Weight Initialization
  • Dense Layers
  • Softmax Layers
  • Dropout
  • Data Augmentation
  • TensorFlow Playground: Visualizing a Deep Net in Action

Segment 3: Deep Learning with Keras, TensorFlow’s High-Level API (60 min)

  • Hands-on Jupyter Notebook Demo: Revisiting our Shallow Neural Network
  • Hands-on Jupyter Notebook Demo: Deep Neural Nets in TensorFlow 2.0
  • Tuning Model Hyperparameters
  • Creating Your Own Deep Learning Project
  • What to Study Next, Depending on Your Interests