O'Reilly logo
live online training icon Live Online training

Gentle, Code-free Intro to Deep Learning and Artificial Intelligence

An Interactive Guide for Technical and Non-Technical Folks Alike

Jon Krohn

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

This live online training surveys all of the modern families of artificial intelligence applications, elucidating exactly what approaches like “deep learning,” “artificial neural networks,” “machine learning,” and “reinforcement learning” are; what it’s possible to do with these approaches today; and what it will be possible to do with them in the future.

Essential theory will be covered following Jon Krohn’s uniquely visual pedagogy, and this theory will be brought to life by interactive demos featuring TensorFlow Playground, an easy-to-use and straightforward-to-understand click-and-point tool.

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

By the end of this live, hands-on, online course, you’ll understand:

  • Speak confidently about any terminology associated with modern A.I., including “deep learning,” “neural networks," and “machine learning”
  • Understand the fundamental theory that facilitates deep learning
  • Appreciate the breadth -- and limitations! -- of A.I. applications today, and the key drivers behind what A.I. will be able to do tomorrow

This training course is for you because...

  • You are in a technical or non-technical role
  • You would like to have a functional understanding of what A.I. is, how it works, and what it’s capable of
  • You would like to be exposed to the complete realm of A.I. applications, with resources for following up on any particular applications that interest you for personal or business purposes

Prerequisites

  • There are absolutely no prerequisites for this training. It assumes no prior technical knowledge pertaining to software development, statistics, machine learning, or any other field.

Materials, downloads, or Supplemental Content needed in advance:

A number of fun click-and-point A.I. demonstrations will be carried out via your web browser; no advance setup or downloads are required.

Resources:

If you’re the kind of person who likes to be exceptionally well-prepared, chapters 1 to 4 of Jon Krohn’s book Deep Learning Illustrated offer detailed coverage of the content that will be the focus of this training.

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: Defining Deep Learning and A.I. (60 min)

  • Concrete Definitions of Interrelated Technical Terms, including Artificial Intelligence, Deep Learning, Artificial Neural Networks, Machine Learning, and Reinforcement Learning
  • Visual, Biological Analogies Enabling a Functional Appreciation of Deep Learning
  • TensorFlow PlayGround -- Visualizing a Deep Neural Net in Action
  • Break + Q&A

Segment 2: Artificial Intelligence Applications (60 min)

  • Machine Vision, including Convolutional Neural Networks, Image Classification, Object Detection, Image Segmentation, Transfer Learning, and Capsule Networks
  • Natural Language Processing, including Recurrent Neural Networks, Long Short-Term Memory Units, and Embedding Meaning in Word Vectors
  • Regression
  • Time-Series Predictions
  • Generative Adversarial Networks for Artistic Creativity including Deep Fakes
  • Deep Reinforcement Learning for Complex Sequential Decision-Making, including Playing Board Games, Video Games, and Autonomous Vehicles
  • Break + Q&A

Segment 3: Essential Deep Learning Theory (60 min)

  • “Whiteboarding” the Fundamental Concepts Underpinning Deep Learning, including Artificial Neurons, Artificial Neural Networks, Activation Functions, Objective Functions, Optimization with Stochastic Gradient Descent, Backpropagation, Dropout, and Data Augmentation
  • Round Two of TensorFlow Playground
  • Software Libraries for Deep Learning
  • Resources for Getting Started with the Development of Deep Learning and Artificial Intelligence Applications