We closed this forum 18 June 2010. It has served us well since 2005 as the ALPHA forum did before it from 2002 to 2005. New discussions are ongoing at the new URL http://forum.processing.org. You'll need to sign up and get a new user account. We're sorry about that inconvenience, but we think it's better in the long run. The content on this forum will remain online.
Index › Discussion › Exhibition › Mouse-writing Recognition with a Neural Network
‹ Previous Topic | Next Topic ›
Page Index Toggle Pages: 1
Mouse-writing Recognition with a Neural Network (Read 849 times)
haroldsoh
Mouse-writing Recognition with a Neural Network
Apr 2nd, 2009, 4:39am  
Hi everyone!

I've been using Processing for a few months and it's just fantastic! Thanks to all the developers who make this software possible.  Smiley

Today, I'm sharing a neural network that recognizes mouse/hand-written symbols. To try it out, head over to:

http://www.haroldsoh.com/haroldsoh.com/Downloads/Entries/2009/3/16_Handwriting_Recognition_with_a_Neural_Network..html

I suggest reading the tutorial before randomly clicking around. It's definitely in the alpha stage and I'm pretty new to Processing so, I welcome comments, suggestions and bug reports! If you find it helpful and use it, please let me know too.

Also, please note that the source code is quite ugly right now but I hope most can figure out how it works. I'll be improving it over time.

There's also a simple infectious disease simulator (using cellular automata) you can find on my downloads page:

http://www.haroldsoh.com/haroldsoh.com/Downloads/Downloads.html

I welcome feedback on this too! Enjoy!

- Harold
Back to top
 
 
WebDext
Re: Mouse-writing Recognition with a Neural Network
Reply #1 - Apr 2nd, 2009, 11:33am  
This is very cool, I've always been interested in seeing a working neural net implementation but I never got around to finding one. Very impressive I'll want to pick apart your code a bit when I have time.

Jack
Back to top
 
WWW JacksEvilClone  
Page Index Toggle Pages: 1
‹ Previous Topic | Next Topic ›