Difference between revisions of "Machine Learning Experiments"

From Software Studies
Jump to navigation Jump to search
Line 12: Line 12:
===RNN focus===
===RNN focus===
*[http://karpathy.github.io/2015/05/21/rnn-effectiveness/ The Unreasonable Effectiveness of Recurrent Neural Networks] (2015) by Andrej Karpathy
*[http://karpathy.github.io/2015/05/21/rnn-effectiveness/ The Unreasonable Effectiveness of Recurrent Neural Networks] (2015) by Andrej Karpathy
===Nueral Network===
*[https://medium.freecodecamp.org/how-to-create-a-neural-network-in-javascript-in-only-30-lines-of-code-343dafc50d49 How to create a Neural Network in JavaScript in only 30 lines of code] (2017) by Per Harald Borgen, see sceencast [https://scrimba.com/casts/cast-1980 here]. Source code [https://github.com/siusoon/ML_neuralnetworkcreation here]


==Examples with source code==
==Examples with source code==

Revision as of 08:31, 29 August 2017

Introduction to Machine Learning

Cultural matters with Machine Learning

Technical explanation on Machine Learning

RNN focus

Nueral 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

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