Difference between revisions of "Machine Learning Experiments"

From Software Studies
Jump to navigation Jump to search
Line 41: Line 41:
===Workshop===
===Workshop===
*[http://www.spacestudios.org.uk/art-technology/counting-to-4-0-1-2-3-data-collection-as-art-practice-protest/ Counting to 4: 0, 1, 2, 3 – Data Collection as Art Practice & Protest] (2017) by Caroline Sinders
*[http://www.spacestudios.org.uk/art-technology/counting-to-4-0-1-2-3-data-collection-as-art-practice-protest/ Counting to 4: 0, 1, 2, 3 – Data Collection as Art Practice & Protest] (2017) by Caroline Sinders
===Demo===
*[https://teachablemachine.withgoogle.com/ Teachable Machine], example [https://www.youtube.com/watch?v=oP8-_0ZyY3U&feature=youtu.be Rock out by wiggling your fingers]


==Learning resource==
==Learning resource==

Revision as of 14:02, 5 October 2017

Introduction to Machine Learning

Cultural matters with Machine Learning

Technical explanation on Machine Learning

RNN focus

Neural Network

Examples with source code

Text related

  • 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

Image related

Projects

Text related

Artworks

Exhibition

Workshop

Demo

Learning resource

Teaching Machine Learning

Experiments/Tests

  • Running spam data with RecurrentJS in a local browser (Winnie)
Running spam data with RecurrentJS
  • Running a jpg file with ConvNetJS in a local browser (Winnie)
Learning a jpg file with ConvNetJS
  • Running a PNG file with Synaptic.js in a local browser (Winnie)
Learning a png file with Synaptic
  • Running a customized neural network in a local browser (Winnie)
Learning XOR with Synaptic