Machine Learning Experiments

Introduction to Machine Learning

• Machine Learning for Creative Media [Video] 10 series workshop by Gene Kogan
• A Return to Machine Learning [Video] by Kyle McDonald
• The 7 steps of Machine Learning (2017) [Video] by Yufeng/Google Cloud
• A visual introduction to machine learning by r2d3.
• Recurrent Neural Network Tutorial for Artists - with handwriting generation demo in p5.js
• Deep Learning: A Critical Appraisal by Gary Marcus

Cultural matters with Machine Learning

• Kate Crawford and Trevor Paglen, “Excavating AI: The Politics of Training Sets for Machine Learning (September 19, 2019) https://excavating.ai
• The six series of Untold History of AI by Oscar Schwartz
• Parisi, Luciana, "Reprogramming Decisionism", e-flux , Oct, 2017
• Kate Crawford and Vladan Joler, “Anatomy of an AI System: The Amazon Echo As An Anatomical Map of Human Labor, Data and Planetary Resources,” AI Now Institute and Share Lab, (September 7, 2018) https://anatomyof.ai
• The Trouble with Bias NIPS 2017 Keynote by Kate Crawford
• Artificial Unintelligence: How Computers Misunderstand the World by Meredith Broussard
• Design Justice, A.I., and Escape from the Matrix of Domination (2018) by Sasha Costanza-Chock
• Entanglement: Machine learning and human ethics in driver-less car crashes (2017) by Maya Indira Ganesh
• Machine Learning and the Complexities of Human Emotions by Caroline Sinders
• Biased bots: Human prejudices sneak into AI systems by Joanna Bryson
• The Temporality of Artificial Intelligence (2017) by Kathryn Hume
• Mackenzie Adrian, The production of prediction: What does machine learning want?,European Journal of Cultural Studies2015, Vol.18(4-5) 429–445
• In the data: interdisciplinary modes of machine learning by Adrian Mackenzie
• Automating Aesthetics: Artificial Intelligence and Image Culture (2017) by Lev Manovich
• Ed Finn, "Building the Star Trek Computer," in What Algorithms Want, MIT Press, 2017, pp. 57-85.
• Mackenzie Adrian, Machine Learners:Archaeology of a Data Practice, MIT Press, 2017
• The Author Function: Imitating Grant Allen with Queer Writing Machines(2017) by Tiffany Chan (with source code)
• Cox, Geoff, Ways of machine seeing. Unthinking Photography, 2016.
• Miyazaki, Shintaro, Take Back the Algorithms! A Media Theory of Commonistic Affordance, (face recognition as a case), 2019.

Technical explanation on Machine Learning

RNN/LSTM focus

• The Neural Aesthetic @ ITP-NYU, Fall 2018 - Lecture 8: Recurrent neural networks (2018) by Gene Kogan
• Understanding LSTM Networks (2015) by Christopher Colah
• The Unreasonable Effectiveness of Recurrent Neural Networks (2015) by Andrej Karpathy
• Visualizing and Understanding Recurrent Networks (Video) (2015) by Andrej Karpathy
• Learning to Forget: Continual Prediction with LSTM (2000) by Felix A. Gers, Jürgen Schmidhuber and Fred Cummins
• Deep Learning Lecture 12: Recurrent Neural Nets and LSTMs (video) (2015) by Nando de Freitas (start at 4:10)

Neural Network

• How to create a Neural Network in JavaScript in only 30 lines of code (2017) by Per Harald Borgen, see sceencast here. Source code here
• Neural Networks in 100 lines of pure Python (2019) by Julian Eisenschlos

Data Processing

• Preprocessing in Data Science (Part 1): Centering, Scaling, and KNN by Hugo Bowne-Anderson

Examples with source code

Mixed media (text/image)

• ML5.js library developed by NYU ITP, text training tutorial here

Text related

• text predictor by Greg Surma (python 2.7/3.+ with tensorflow (RNN+LSTM) and his article here: Text Predictor - Generating Rap Lyrics with Recurrent Neural Networks (LSTMs)
• Tom-Chang-Deep-Lyrics | 基於 LSTM 深度學習方法研發而成(2018) by 林志傑 (Python with bleach-1.5.0 html5lib-0.9999999 tensorboard-1.8.0 tensorflow-1.8.0)
• Semantic similarity chatbot (with movie dialog) by Allison Parrish
• Chinese receipt OCR using Tensorflow | SpikeFlow (Blog | Github)
• Recurrentjs by Andrej Karpathy, mainly for text training. "Sentences are input data and the networks are trained to predict the next character in a sentence." + his interview on why javascript and machine learning.
• Re-appropriation of Recurrentjs by UCL Creative Hub

Chinese text related

• 达观数据：综述中英文自然语言处理的异和同 (2019) by 机器之心

Image related

• Image paint: 1/ ConvNetJS Library by Andrej Karpathy 2/ Synaptic.js by Synaptic
• Image-to-Image Demo: Interactive Image Translation with pix2pix-tensorflow by Christopher Hesse

Sound related

• Deep roll by Tero Parviainen | source code built with TensorFlow and js

Projects

Text related

• THE TEXT-GENERATING RNN DEMO by Ilya Sutskever
• Handwriting Generation Demo by Alex Graves
• Obama RNN by Samim
• RNN Bible on Twitter
• Notes on remixing Noon, generative text and Markov chains by Rev Dan Catt

Artworks

• Errant: The Kinetic Propensity of Images by Hector Rodriguez (2018)
• An algorithm watching a movie trailer by Andreas Refsgaard and Lasse Korsgaard
• of the soone by Sofian Audry (2017)
• Critter Compiler prototype by Helen Pritchard (2016)
• Cloud index by James Bridle | Read his interview here on James Bridle: Machine Learning in Practice
• Big Data Poetry by David Jhave Johnston
• Learning to see: Hello, World! (2017) by Memo Akten. More here

Examples/Performance/Speculative design

• Examples of Wekinator
• AYA pushes back by Marie Louise Juul Søndergaard

Exhibition

• Artists & Robots (2017) at the Astana Contemporary Art Center in Kazakhstan
• Artificial Intelligence: The Other I (2017) Ars Electronica

Workshop

• The Work of Art in the Age of Artificial Intelligence Workshop (2018) by media art curator Natalia Fuchs and media artist Helena Nikonole
• Counting to 4: 0, 1, 2, 3 – Data Collection as Art Practice & Protest (2017) by Caroline Sinders

Conference

• Music and Artificial Intelligence - Pasts and Futures, Opportunities and Risks (2019) organized by Georgina Born, AIAS, Aarhus University
• Art Machines: International Symposium on Computational Media Art (2019) organized by School of Creative Media, City University of Hong Kong
• international conference »Encoding Cultures. Living Amongst Intelligent Machines«(2018)
• [https://aoir.org/aoir2018/preconfwrkshop/#CL The Cultural Life of Machine Learning: An Incursion into Critical AI Studies

Preconference Workshop] (2018)

Demo/Experimental Projects

• Teachable Machine, example Rock out by wiggling your fingers, source code here
• Giorgio Cam by Eric Rosenbaum and Yotam Mann, source code here
• Webcam Pacman by BANDAI NAMCO Entertainment Inc.
• P5js KNN demos by Andreas Refsgaard
• TensorFlow.js gallery

Learning resource

• ml5: Friendly Open Source Machine Learning Library for the Web by Daniel Shiffman and ml5.js collaborators
• Daniel Shiffman's Nature of Code: Neural networks| video
• Machine Learning for Artists by Gene Kogan and Francis Tseng
• Machine Learning for Muscians and Artists by Rebecca Fiebrink (main), Laetitia Sonami (guest) and Baptiste Caramiaux (guest)
• Machine Learning, taught by Andrew Ng
• Machine Learning A-Z™: Hands-On Python & R In Data Science
• Neural Network Evolution Playground with Backprop NEAT
• ConvNetJS: Deep Learning in the Browser [Video] by Christoph Körner (more technical)
• CS231n: Convolutional Neural Networks for Visual Recognition by Standford
• Machine Learning resource list by David Jhave Johnston
• Machine Learning Magic for Your Javascript Application (Google I/O'19) with Tensorflow.js [Video] (2019)
• Deep Convolutional Generative Adversarial Network Step by step with python code walkthrough

Teaching Machine Learning

• Machine Learning for Introductory Physical Computing Curricula by Ali Momeni

Experiments/Tests

• 08/2019: Runway's image to text prediction: "a collage of photos of a man on a motorcycle"

• 08/2019: Runway's YOLACT - computer and algorithm shift our attention to something else. A lid cannot be recognized but that's the key object in the photo (ways of human seeing) actually. May be the training data contains mostly western objects.
  
  
• 08/2019: Running LSTM/tensorflow with text_predictor.py and ml5 training

• 12/2018: Try running LSTM/tensorflow training on chinese text with python (again following text predictor)

• 11/2018: Try running LSTM/tensorflow training with Python (following text predictor)from my PhD thesis text

• 11/2018: Try running local ml5 + python training with English text (multiple manifestos) and generate 10000 characters text from multiple manifestos

• 06/2018: Try running LSTM ml5js with training simplied chinese data. Source from weiboscope 2012 week 1 deleted text

• 06/2018: Running LSTM ml5js example with my own training data

• 2018: Running ml5.js example - Simple LSTM Generator Example on a local browser

• Running ml5.js example - Simple Image Classification Example on a local browser

• Running spam data with RecurrentJS on a local browser

• Running a customized neural network on a local browser

• Running a PNG file with Synaptic.js on a local browser

• Running a jpg file with ConvNetJS on a local browser