‘Machine Learning for Designers’ workshop

On Wednesday Péter Kun, Holly Robbins and myself taught a one-day workshop on machine learning at Delft University of Technology. We had about thirty master’s students from the industrial design engineering faculty. The aim was to get them acquainted with the technology through hands-on tinkering with the Wekinator as central teaching tool.

Photo credits: Holly Robbins
Photo credits: Holly Robbins

Background

The reasoning behind this workshop is twofold.

On the one hand I expect designers will find themselves working on projects involving machine learning more and more often. The technology has certain properties that differ from traditional software. Most importantly, machine learning is probabilistic in stead of deterministic. It is important that designers understand this because otherwise they are likely to make bad decisions about its application.

The second reason is that I have a strong sense machine learning can play a role in the augmentation of the design process itself. So-called intelligent design tools could make designers more efficient and effective. They could also enable the creation of designs that would otherwise be impossible or very hard to achieve.

The workshop explored both ideas.

Photo credits: Holly Robbins
Photo credits: Holly Robbins

Format

The structure was roughly as follows:

In the morning we started out providing a very broad introduction to the technology. We talked about the very basic premise of (supervised) learning. Namely, providing examples of inputs and desired outputs and training a model based on those examples. To make these concepts tangible we then introduced the Wekinator and walked the students through getting it up and running using basic examples from the website. The final step was to invite them to explore alternative inputs and outputs (such as game controllers and Arduino boards).

In the afternoon we provided a design brief, asking the students to prototype a data-enabled object with the set of tools they had acquired in the morning. We assisted with technical hurdles where necessary (of which there were more than a few) and closed out the day with demos and a group discussion reflecting on their experiences with the technology.

Photo credits: Holly Robbins
Photo credits: Holly Robbins

Results

As I tweeted on the way home that evening, the results were… interesting.

Not all groups managed to put something together in the admittedly short amount of time they were provided with. They were most often stymied by getting an Arduino to talk to the Wekinator. Max was often picked as a go-between because the Wekinator receives OSC messages over UDP, whereas the quickest way to get an Arduino to talk to a computer is over serial. But Max in my experience is a fickle beast and would more than once crap out on us.

The groups that did build something mainly assembled prototypes from the examples on hand. Which is fine, but since we were mainly working with the examples from the Wekinator website they tended towards the interactive instrument side of things. We were hoping for explorations of IoT product concepts. For that more hand-rolling was required and this was only achievable for the students on the higher end of the technical expertise spectrum (and the more tenacious ones).

The discussion yielded some interesting insights into mental models of the technology and how they are affected by hands-on experience. A comment I heard more than once was: Why is this considered learning at all? The Wekinator was not perceived to be learning anything. When challenged on this by reiterating the underlying principles it became clear the black box nature of the Wekinator hampers appreciation of some of the very real achievements of the technology. It seems (for our students at least) machine learning is stuck in a grey area between too-high expectations and too-low recognition of its capabilities.

Next steps

These results, and others, point towards some obvious improvements which can be made to the workshop format, and to teaching design students about machine learning more broadly.

  1. We can improve the toolset so that some of the heavy lifting involved with getting the various parts to talk to each other is made easier and more reliable.
  2. We can build examples that are geared towards the practice of designing IoT products and are ready for adaptation and hacking.
  3. And finally, and probably most challengingly, we can make the workings of machine learning more transparent so that it becomes easier to develop a feel for its capabilities and shortcomings.

We do intend to improve and teach the workshop again. If you’re interested in hosting one (either in an educational or professional context) let me know. And stay tuned for updates on this and other efforts to get designers to work in a hands-on manner with machine learning.

Special thanks to the brilliant Ianus Keller for connecting me to Péter and for allowing us to pilot this crazy idea at IDE Academy.

References

Sources used during preparation and running of the workshop:

  • The Wekinator – the UI is infuriatingly poor but when it comes to getting started with machine learning this tool is unmatched.
  • Arduino – I have become particularly fond of the MKR1000 board. Add a lithium-polymer battery and you have everything you need to prototype IoT products.
  • OSC for Arduino – CNMAT’s implementation of the open sound control (OSC) encoding. Key puzzle piece for getting the above two tools talking to each other.
  • Machine Learning for Designers – my preferred introduction to the technology from a designerly perspective.
  • A Visual Introduction to Machine Learning – a very accessible visual explanation of the basic underpinnings of computers applying statistical learning.
  • Remote Control Theremin – an example project I prepared for the workshop demoing how to have the Wekinator talk to an Arduino MKR1000 with OSC over UDP.

Week 169

Fiona Raby once told me that the majority of her work with students at the RCA was about psychology. After a week like this, I can see where she’s coming from. Without going into too much detail, I had my work cut out for me with a new group of students who I will be working with on a design research project at the HKU. After a first meeting with the team and a kick-off with the client the next day, it became clear I was dealing with a group with some serious motivational issues. The trick was to figure out where it all was coming from. To do this it was vital to try and see things as they really are in stead of as they were presented to me by the group. After several additional sessions (messing with my schedule but that comes with the territory) I had it figured out more or less and have formulated a plan to deal with it. Psychology.

In between all that craziness my week consisted of:

  • Working with my two new interns at Hubbub. We reflected on their experiences at the Natural Networking Festival and presented a post-mortem of the first game to Thieu after attending one of the Learning Lab meetups.
  • Sketching out additions to the PLAY Pilots website necessary to support the Zesbaans installation for the Netherlands Film Festival. These will launch next week in time for the installation’s unveiling on Thursday.
  • Presenting my preliminary list of interactive works suitable for next year’s Tweetakt festival. This is my first time curating an event other than This happened. I am keen to mash up playful interaction design with the fringes of game design and it seems Tweetakt are up for it too. Happy days.
  • Another full day of work on Maguro. Best part of which was a few quiet hours to bang out a first playable paper prototype of the game. Convergence is a bitch but always rewarding when it happens.
  • Today, I hung out at BUROPONY and took care of a few odds and ends for their website. In return work has started on a last bit of Hubbub corporate identity: a design for the box to hold our business-slash-collectible playing cards.

And with that I am signing off. A train is taking me from Rotterdam to Utrecht, perhaps I will be in time to catch the tail end of friday drinks at the Dutch Game Garden. Never a dull moment there.

“Stay hungry, stay foolish”

I graduated from the Utrecht School of the Arts in 2002. Now, less than seven years later, I am mentoring a group of five students who will be doing the same come September this year. I took a photo of them today, here it is:

Bright young bunch

From left to right, here’s who they are and what they’re up to:

  • Christiaan is tech lead on Hollandia, an action adventure game inspired by Dutch folklore. His research looks at ways to close the gap between creatives and technologists in small teams, using agile techniques.
  • Kjell is designing a series of experimental games using voice as their only input. He’s researching what game mechanics work best with voice control.
  • Maxine is game designer on the aforementioned Hollandia game. Her research looks at the translation of the play experience of physical toys to digital games. (In of Hollandia, you’ll be using a Wiimote to control the spinning top used by the heroine.)
  • Paul is building a physics-based platform puzzle game for two players. His research looks at the design of meaningful collaborative play.
  • Eva is making a space simulation game with realistic physics and complex controls. She’s researching what kinds of fun are elicited by such games.

Practically speaking, mentoring these guys means that I see them once a week for a 15-minute session. In this we discuss the past week’s progress and their plans for the next. They’ve set their own briefs, and are expected to be highly self-reliant. My task consists of making sure they stay on track and their work is relevant, both from an educational and a professional perspective. It’s challenging work, but a lot of fun. It forces me to make explicit the stuff I’ve picked up professionally. It’s also a lot about developing a sense for where each student individually can improve and encouraging them to challenge themselves in those areas.

I’m looking forward to seeing what they’ll deliver come September, when it’s their turn to graduate, and go out to conquer the world.

What I’ve been up to lately

You might be wondering what’s been going on at the Leapfrog studio lately, since I haven’t really posted anything substantial here in a while. Quite some stuff has happened — and I’ll hopefully get back into posting longer articles soon — but for now, here’s a list of more or less interesting things I have been doing:

This happened – Utrecht

We had our first This happened – Utrecht on November 3. I think we succeeded in creating an event that really looks at the craft of interaction design. I’m happy to say we’re planning to do three events next year — all at Theater Kikker in Utrecht — and we’ve got lots of cool speakers in mind. If you want to make sure you won’t miss them, subscribe to our newsletter (in Dutch).1

Teaching

My students are nearing the end of their project. They’ve been hard at work creating concepts for mobile social games with a musical component; they came up with 20 in total. Now they’re prototyping two of them, and I must say it’s looking good. They’ll have to present the games to the project’s commissioner — a major mobile phone manufacturer — somewhere the beginning of January 2009. I hope to be able to share some of the results here afterwards.

Office space

Since December 1 I am a resident of the Dutch Game Garden’s Business Club. That means I now have a nice office smack in the centre of Utrecht. The building’s home to lots of wonderful games companies, some, like me, operating on the fringes — like FourceLabs and Monobanda. If you’re curious and would like to drop by for a tour, a coffee and some conversation, let me know.

Brainstorm

I was invited do help compose one of the cases for the ‘Grote Amsterdamse Waterbrainwave’. A one-day brainstorm in which 45 students from various institutions were asked to come up with water-related innovations that would make the Netherlands a significant global player once again. It was organised by the Port of Amsterdam, Waternet and Verleden van Nederland2. I also attended the day itself as an outside expert on games and the creative industry in general. Read a report of the event at FD.nl (in Dutch).

Book

Dan Saffer’s book Designing Gestural Interfaces has been published by O’Reilly and is now available. Turn to page 109 and you’ll find a storyboard by yours truly used for illustration purposes. That’s the first time any work of mine is featured in print, so naturally I’m quite proud. I have yet to receive my copy, but got a sneak peek this weekend and I must say it looks promising. If you’re a designer needing to get up to speed with multi-touch, physical computing and such, this should be a good place to start.

That’s about it for now. There’s a lot of exciting stuff in the works, the outcomes of which I will hopefully be able to share with you in 2009.

  1. The creators of This happened in London have been nominated for a best of the year award by the Design Museum, by the way. Well-deserved, I would say! []
  2. A cross-media campaign aimed at increasing awareness of Dutch national history. []

Teaching design for mobile social play

Last week, the group project I am coaching at the Utrecht School of the Arts kicked off. The project is part of the school’s master of arts program. The group consists of ten students with very different backgrounds, ranging from game design & development to audio design, as well as arts management, media studies, and more. Their assignment is to come up with a number of concepts for games that incorporate mobile phones, social interactions, audio and the web. Nokia Research Center has commissioned the project, and Jussi Holopainen, game design researcher and co-author of Patterns in Game Design, is the client. In the project brief there is a strong emphasis on sketching and prototyping, and disciplined documentation of the design process. The students are working full time on the project and it will run for around 4 months.

I am very happy with the opportunity to coach this group. It’s a new challenge for me as a teacher – moving away from teaching theory and into the area of facilitation. I am also looking forward to seeing what the students will come up with, of course, as the domain they are working in overlaps hugely with my interests. So far, working with Jussi has proven to be very inspirational, so I am getting something out of it as a designer too.

On presentations

One of the most enjoyable things about attending conferences is seeing a lot of people presenting in various ways. A while ago I challenged my own presenting skills by doing a Pecha Kucha. Today, I attended a class (part of a didactics course) on giving lectures. Two prominent lecturers (Giep Hagoort and Jeroen van Mastrigt) from within the Utrecht School of Arts gave us a taste of their own unique presentation format and the way they prepared for a talk.

This triggered some things in my head, such as stuff I’d seen before on the web and that could be helpful to the people attending the class. A lot of them didn’t seem to be too familiar with it, so I’ve decided to collect them here. Maybe they’ll come in handy to those who pass by here: