COMPPX18 | Intro

Results

Laura, Mike, Jony:

• Repo: https://github.com/micromic5/FaceEmotionGuitarHero
• Demo: https://www.massol.me/upload/comppx/laura-mike-jony-face-emotion-guitar-hero/
• Presentation: https://www.dropbox.com/s/kkj8jpk532cs01q/Laura_Mike_Jony_Comppx.pdf?dl=0

Simon, David:

• Repo: https://github.com/TheCell/generativeMachinelearning
• Demo: https://massol.me/upload/comppx/david-simon-generativeml

Yannick, Dan:

• Repo: https://github.com/yannickbaettig/comppx
• Demo: https://yannickbaettig.github.io/comppx
• Presentation: https://www.dropbox.com/s/z1w6wjo4vvt4r4i/Yannick_Dan_Comppx.pdf?dl=1

Marlon:

• Zip: https://www.dropbox.com/s/qvc2w9l77cop7l5/Marlon_Abgabe.zip?dl=1

Regula, Valentin:

• Repo: https://github.com/V4L3/wannabeart
• Demo: https://v4l3.github.io/wannabeart/ (only works on Chrome)

Aytac, Orell:

• Demo: http://cast.it-touch.ch/rapbotmania

Intro

In this module we will explore different applications of ML/AI/DL with a particular focus on design and art. We will first learn how neural networks work with simple code examples, then we will experiment with different techniques of Deep Learning:

• DL applied to Computer Vision (image classification, objects detection, pose estimation…)
• Generative Deep Learning (DeepDream, style transfer, Pix2Pix / CycleGAN…)
• etc…

Once we get a good grasp of the different techniques, we will experiment further by building our own ‘AI’ project.

Before starting

• Learn Python the hard way: to (re)learn your basic in Python
• Google’s Python Class: concise and clear
• CodeAcademy Python: Code Academy Python class
• W3School js: JS simple tutorials
• CodeAcademy JS: Code Academy JS class
• Eloquent JS: Eloquent JS

Tools

1. Wekinator

Wekinator is a software allowing anyone to use machine learning to build new musical instruments, gestural game controllers, computer vision and so on. Wekinator is using OSC protocol and can be used with pretty much any type of programing language. We will use it with Processing.

• Example
• Quick Start Pack
• Course

2. ML5.js

ML5.js is a simple JavaScript ML library for the web based on tensorflow.js.

• Getting started
• Experiments
• Git source

3. Synaptic.js

The JavaScript architecture-free neural network library for node.js and the browser

• Documentation
• Github
• Another good tutorial

4. Brain.js

Neural networks in JavaScript, simple and playful.

• Great tutorial 01
• Tutorial 02
• Tutorial 03

5. Tensorflow.js

A JavaScript library with a more advanced set of options, also for the web.

• Getting Started
• Tutorials
• Keynote
• Examples
• Video Tutorials

6. Magenta.js

Magenta.js is a collection of TypeScript libraries for doing inference with pre-trained Magenta models. All libraries are published as npm packages.

• Demos
• Blog

7. Keras

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation

• Getting Started
• Tutorials

8. ML4A OFX

A collection of real-time interactive applications and associated scripts for working with machine learning. ML4A-OFX is running on OpenFrameworks.

• Guides
• Git

9. OFX MSATensorflow

OpenFrameworks addon for Google’s graph based machine intelligence / deep learning library TensorFlow.

Schedule

Week 01

• Intro: General
  • About the course (communication, resources, deliverables, etc…)
• ML / AI / DL
  • History & Example
• Intro: Tools
  • Keras, TFJS, ML5JS, etc…

Week 02

• Students intro
• Inner working of a Neural Network
• NN : Toy Neural Network
  • Build together a simple neural net
  • Create simple classification tasks

Week 03

• Machine Learning Project Checklist
• Training a NN: Intro to tools
  • Keras
  • ML5js
  • Paperspace (tbc)

Week 04 (self study)

• Machine Learning for computer vision (ConvNets)

Week 05

• Machine Learning for computer vision (ConvNets)
• Review Convnets

Week 06

• Generative models: LSTM, RNN
• Making music with RNN

Week 07

• Generative models:
  • Deep Dream
  • Style Transfer
  • VAE
  • GAN
• Status Quo
• Projects dicussion

Week 08

• Creating datasets
• Making your models ‘available’
  • Exporting models
  • API

…

Content