Machine Learning for Designers

Video description

Recent advances in machine learning (ML), natural language processing, image recognition, content personalization, and behavior prediction are radically changing the capabilities of software and the interfaces people use to interact with that software.

This course provides an insider's look at contemporary ML technologies and how these technologies are transforming the next generation of computing interfaces for search engines, intelligent assistants, connected homes, and open-world video games. Created for designers new to the world of machine learning, the course provides an explanation of the basic concepts of ML, offers a hands-on introduction to ML's core toolsets, and surveys the upcoming opportunities for designers with ML skills.

  • Understand what machine learning and deep learning really mean; and their impacts on UX/UI design
  • Learn how ML improves the ability to engage with and understand users
  • Discover how machine learning systems differ from traditional computing platforms
  • Learn to use Google's TensorFlow machine learning toolkit to build, train, visualize, and configure neural networks
  • Explore related development, deployment and workflow management toolsets: Docker, Launchbot, and Jupyter Notebooks
  • Gain hands-on ML experience by building a web app with a customized image recognition system
Patrick Hebron is a scientist-in-residence and adjunct graduate professor at NYU’s Interactive Telecommunications Program, where he leads programs focused on the intersection of art and technology. He is the founder of Foil, a digital design tool company, is author of the O'Reilly e-book, "Machine Learning for Designers," and he has worked as a software developer and design consultant for numerous corporate clients and cultural institutions.

Table of contents

  1. Why Design For Machine Learning Is Different
    1. Course Intro 00:01:44
    2. About The Author 00:01:05
    3. Boolean Vs Fuzzy Logic 00:02:26
    4. Explicit Programming Vs Experiential Training In Machine Learning 00:03:18
    5. Procedural Precision Vs Intuitive Approximation With Machine Learning 00:02:13
    6. Finding The Right Tool For The Job 00:01:06
  2. What Is Machine Learning?
    1. Deductive And Inductive Reasoning 00:01:20
    2. Mechanical Induction 00:04:29
    3. The Major Types Of Learning Algorithms 00:04:57
    4. What Is Deep Learning? 00:02:38
    5. Building Intuition For Machine Learning Problems 00:05:41
  3. Getting Started With Machine Learning Workflows
    1. Preliminary Look At The Stages Of A Machine Learning Workflow 00:04:57
    2. Why Machine Learning Requires Special Tools And Workflows 00:03:39
    3. Streamlining Machine Learning Workflows With Docker 00:01:44
    4. Getting Started With Docker 00:01:24
    5. Getting Started With Launchbot 00:03:14
    6. Getting Started With Jupyter Notebooks 00:02:37
  4. Getting Started With Machine Learning Development
    1. Getting Started With TensorFlow 00:04:25
    2. Setting Up TensorFlow 00:00:38
    3. Graphs And Sessions In TensorFlow 00:03:26
    4. Basic Operations In TensorFlow 00:02:43
    5. Working With Data In TensorFlow 00:03:42
    6. Building And Training A Simple Neural Network In TensorFlow 00:07:43
    7. Visualizing A Simple Neural Network In TensorFlow 00:02:20
  5. Going Deeper With Machine Learning Development
    1. Saving And Restoring Models In TensorFlow 00:01:41
    2. The Dark Art Of Neural Network Configuration 00:04:11
    3. Overfitting And Other Learning Difficulties 00:04:32
    4. Improving Learning Quality 00:04:51
    5. Working With The Inception Image Recognizer In TensorFlow 00:03:20
    6. Performing Transfer Learning On The Inception Image Recognizer In TensorFlow 00:05:22
  6. Integrating Machine Learning Systems Into User-Facing Software
    1. Building A User-Facing Image Recognition Web Application 00:06:03
  7. Reflecting Upon The Design Landscape
    1. Reflecting Upon Design Landscape 00:04:43
  8. Design Opportunities
    1. Parsing Complex Information 00:07:51
    2. Creating Dialogue 00:08:05
  9. Design Challenges
    1. Designing For Uncertainty 00:02:37
    2. Masking Faulty Assumptions 00:03:06
    3. Creating Sanity Checks 00:02:44
  10. How To Continue Your Study Of Machine Learning
    1. Resources For The Further Study Of Machine Learning 00:00:55
    2. Staying Up-To-Date With Advancements In The Field 00:01:13
    3. Emerging Opportunities For Machine-Learning-Enhanced Design 00:01:56
  11. Conclusion
    1. Wrap Up And Thank You 00:00:45

Product information

  • Title: Machine Learning for Designers
  • Author(s): Patrick Hebron
  • Release date: April 2017
  • Publisher(s): Infinite Skills
  • ISBN: 9781491982747