Machine Learning for Interaction Design

Become familiar with the tools and the theory at the intersection of machine learning and interaction design. Add a touch of data-driven intelligence to your prototypes and designs.

Enrol here!

Workshop Dates: Dec 17-21, 2018

Faculty: Andreas RefsgaardGene Kogan

What is Machine Learning?

A hands-on introduction to machine learning with a focus on creating your own artistic and interactive applications.

When programming interactive prototypes, interaction designers traditionally rely on their ability to formulate logical structures and explicit relationships between inputs and outputs through code that executes in a predictable way.

Machine Learning suggests a different kind of logic. Instead of relying on explicit sets of rules to determine a system’s behavior, machine learning models learn by example, by looking for patterns within a set of examples or training data from a designer or performer, and make the rules autonomously so as to conform to the performer’s expectation. This pattern recognition process is somewhat like our own mental processes for learning about the world around us, and provides a lot of new opportunities for interaction designers, especially when dealing with input data too complex to account for via coding.

The workshop will introduce the basics of machine learning in a way that is tailored to interaction designers or participants with no prior experience in machine learning. It will be shown how unsupervised learning can be used to cluster, organise and visualise large quantities of data to gain insights into its composition, and how supervised learning can enable students to train their own models to act upon custom inputs and assign output behaviours to them.

What you will learn:

The students will be provided with a set of easy out-of-the-box tools for training their own machine learning models to work with skeleton, finger or face tracking, webcam and microphone input as well as more advanced tools for unsupervised learning and retrieval/clustering/organization/visualization of big samples of text, sounds or images.

Because machine learning allows the students to handle really complex input data and easily map it to desired outputs this workshop will:

  • Significantly broaden the students’ interaction design toolbox and allow them to imagine a larger range of inputs for future projects
  • Allow students to prototype faster across a range of mediums, by creating customized input/output mappings through example and physical iteration rather than explicitly programming them. This process is more flexible and iterative compared to the more linear and time consuming programming approach
  • Facilitate the creation of custom interfaces for this rapid prototyping, enabling a much more agile collaborative process
  • Provide students with lesser coding skills an alternative approach for making interactive tools and demos
  • Be a hands-on approach to getting familiar with a complex, but increasingly important field
  • Teach students how to use neural networks to create real-time, cross-modal interactions for use in video, installation, live music performance or physical computing

How you will learn it:

Through:

  • Lectures
  • Small assignments + explorations
  • Group project with supervision

Is this for you?

Yes, if you are interested in exploring the world of Machine Learning and how to design for it. Anyone can join – prior coding experience (in a text-based or patch-based programming environment – especially in creative coding frameworks like Processing and OpenFrameworks, or in Python, or Javascript) would be helpful but is not necessary to get the most out of the class.

What do you need to bring to the workshop?

  • Computer
  • OPTIONAL: Any sensors, webcams, microphones, etc you might want to use as an input

Enrol now: There is a maximum number of 20 places available for each workshop, first comes first served. Enrolment will be closed when the workshops are full.