Neural Nets: Difference between revisions
Jump to navigation
Jump to search
Adamcolton (talk | contribs) Created page with "I've been researching neural nets for several years and while I feel that I have a decent grasp on the subject matter, I have not yet produces an interesting demo. [[File:Florea..." |
Adamcolton (talk | contribs) No edit summary |
||
| Line 1: | Line 1: | ||
I've been researching neural nets for several years and while I feel that I have a decent grasp on the subject matter, I have not yet produces an interesting demo. | I've been researching neural nets for several years and while I feel that I have a decent grasp on the subject matter, I have not yet produces an interesting demo. | ||
=Connect 4= | |||
Todo: | |||
*Select only a few of the top champions for mutation - there's not point to creating a mutation of 1 when we're up to 1000 | |||
*Break the make table function off to it's own process | |||
*Possibly create a more competitive model that NNs can reproduce when they win and will die after so many losses | |||
[[File:Floreano-neuroevolution-overview-2008.pdf]] | [[File:Floreano-neuroevolution-overview-2008.pdf]] | ||
[[File:CheckersANN.pdf]] | [[File:CheckersANN.pdf]] | ||
Revision as of 21:37, 18 January 2012
I've been researching neural nets for several years and while I feel that I have a decent grasp on the subject matter, I have not yet produces an interesting demo.
Connect 4
Todo:
- Select only a few of the top champions for mutation - there's not point to creating a mutation of 1 when we're up to 1000
- Break the make table function off to it's own process
- Possibly create a more competitive model that NNs can reproduce when they win and will die after so many losses
File:Floreano-neuroevolution-overview-2008.pdf File:CheckersANN.pdf