#8 Machine Learning

This assignment has three lightweight components, none of which involve writing code:

  1. Looking Outwards #04: Machine Learning (Due 11/9)
  2. Machine Learning Tinkering (Ungraded; Due 11/9)
  3. Viewing: Helena Sarin Lecture Video (Before 11/9)

We may discuss the possible logistics of adding a potential fourth assignment—a machine-learning coding project similar to this “Situated Eye” project given in 2019—after assessing how people are feeling.


1. Looking Outwards #04: Machine Learning (Due 11/9)

Spend about 30 minutes browsing the following online showcases of projects that make use of machine learning and ‘AI’ techniques. More than 500 projects are indexed across these sites.

  • MLArt.co Gallery (a collection of Machine Learning experiments curated by Emil Wallner).
  • AI Art Gallery (online exhibition of the 2019 NeurIPS Workshop on Machine Learning for Creativity and Design). Note: this site also hosts the exhibitions for the 2018 and 2017 conferences.
  • Chrome Experiments: AI Collection (a showcase of experiments, commissioned by Google, that explore machine learning through pictures, drawings, language, and music)

Now:

  • After considering several dozen projects, select one to feature in a Looking Outwards blog post. Restrictions: You may not select a project by your professor, nor by Helena Sarin (who will be visiting our class on Monday 11/9).
  • As usual, include an image of the selected project; a link to information about it, and 100-150 words describing the project and why you found it interesting.
  • Please title this blog post nickname-LookingOutwards04, and categorize the project LookingOutwards-04.

2. Machine Learning Tinkering (Ungraded; Due 11/9)

This assignment has four parts, the purpose of which is to d̶i̶s̶t̶r̶a̶c̶t̶ immerse you in creatively using some machine-learning systems. None entail writing code.

Part 2A: Pix2Pix.

Spend some time with the Image-to-Image (Pix2Pix) demonstration page by Christopher Hesse. Experiment with edges2cats and some of the other interactive demonstrations (such as facades, edges2shoes, etc.). You are asked to:

  • Create at least 3 different designs. Screenshot your work so as to show both your input and the system’s output. Embed these screenshots into a blog post.
  • Write a reflective sentence about your experience using this tool.
  • Title your blog post nickname-Pix2Pix, and categorize your blog post with the WordPress category, 08-Pix2Pix.
Part 2B: ArtBreeder

ArtBreeder is an interactive and participatory machine-learning based tool developed by CMU BCSA alum, Joel Simon.

  • Create an account on ArtBreeder.
  • You are asked to spend a half-hour zoning out with ArtBreeder. Using ArtBreeder’s “General” model, develop at least two images.
  • Using your choice of the Portraits, Album Covers, Landscapes, or Anime Portraits models, create at least one additional design.
  • Embed your results in a blog post entitled nickname-ArtBreeder and Categorized, 08-ArtBreeder.
  • In your blog post, write a reflective sentence or two about your experience using this tool.
Part 2C: Talk to Transformer (GPT-2)

Use the “TalkToTransformer” (InferKit) tool by Adam King, built using Open AI’s GPT-2 language model, to generate some samples of text which interest you.

  • TalkToTransformer: Generate two samples of text with this tool. (Use the “Custom Prompt” setting from the pulldown menu.)
  • Embed the text experiments in a blog post. Use boldface to indicate which words were provided by you as inputs to the system.
  • Title your blog post nickname-GPT2, and categorize your blog post with the WordPress category, 08-GPT2.
  • In your blog post, write a reflective sentence or two about your experience using this tool.
Part 2D: Teachable Machine

Google’s Teachable Machine tool allows you to train a (neural-network-based) image recognition system, in the browser, without code. Some of the people contributing to the project include recent CMU alumni Irene Alvarado, Gautam Bose and Lucas Ochoa.

  • Train a detector using your computer’s webcam and Google’s Teachable Machine
  • Record an animated GIF of your detector in action.
  • Embed your GIF in a blog post entitled nickname-TeachableMachine, and categorize your blog post with the WordPress category, 08-TeachableMachine.
  • In your blog post, write a reflective sentence or two about your experience using this tool.


3. Viewing: Helena Sarin Lecture Video (Before 11/9)

Before our class on Monday, November 9:

  • Please watch the 41-minute video below, a 2019 Eyeo Festival lecture by artist Helena Sarin.
  • Helena will be visiting our class 11/9. Please come prepared for her visit with two questions.