<feed xmlns='http://www.w3.org/2005/Atom'>
<title>ctak/include/nn.c, branch action_array</title>
<subtitle>An implementation of Tak and a computer opponent in C</subtitle>
<id>https://git.l-3.space/ctak/atom/include/nn.c?h=action_array</id>
<link rel='self' href='https://git.l-3.space/ctak/atom/include/nn.c?h=action_array'/>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/'/>
<updated>2023-01-21T21:00:57Z</updated>
<entry>
<title>might as well enable size 6</title>
<updated>2023-01-21T21:00:57Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2023-01-21T18:30:45Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=72c5056c5aa614d9a86f8b760955cfcf96c44be4'/>
<id>urn:sha1:72c5056c5aa614d9a86f8b760955cfcf96c44be4</id>
<content type='text'>
Same network architecture, same training principle. Predictably this is
too slow.

Also statically allocate state in driver programmes.
</content>
</entry>
</feed>
