Difference between revisions of "Machine Learning Experiments"
Jump to navigation
Jump to search
| Line 1: | Line 1: | ||
==References== | ==References== | ||
==Examples== | ==Examples with source code== | ||
* Chinese receipt OCR using Tensorflow | SpikeFlow ([https://deeperic.wordpress.com/2017/02/18/chinese-ocr-tensorflow/ Blog] | [https://github.com/deeperic/SpikeFlow Github]) | * Chinese receipt OCR using Tensorflow | SpikeFlow ([https://deeperic.wordpress.com/2017/02/18/chinese-ocr-tensorflow/ Blog] | [https://github.com/deeperic/SpikeFlow Github]) | ||
* [https://github.com/karpathy/recurrentjs Recurrentjs], mainly for text training. "Sentences are input data and the networks are trained to predict the next character in a sentence." | * [https://github.com/karpathy/recurrentjs Recurrentjs], mainly for text training. "Sentences are input data and the networks are trained to predict the next character in a sentence." | ||
==Projects== | |||
[http://www.cs.toronto.edu/~ilya/fourth.cgi?prefix=This+is+a+piece+of&numChars=100 THE TEXT-GENERATING RNN DEMO] | |||
==Learning resource== | ==Learning resource== | ||
Revision as of 21:59, 6 July 2017
References
Examples with source code
- Chinese receipt OCR using Tensorflow | SpikeFlow (Blog | Github)
- Recurrentjs, mainly for text training. "Sentences are input data and the networks are trained to predict the next character in a sentence."
Projects
Learning resource
- Daniel Shiffman's Nature of Code: Neural networks| video
- Machine Learning for Artists by Gene Kogan and Francis Tseng
- Machine Learning A-Z™: Hands-On Python & R In Data Science
Experiments/Tests
- Running spam data in RecurrentJS
