There is Gene Sher's neural net / artificial life work,
e.g.:<div><br></div><div>https://github.com/CorticalComputer/DXNN</div><div><br></div><div>http://www.springer.com/us/book/9781461444626</div><div><br></div><div><br></div><div><br></div><div><br><br><div
id="cm_replymail_content_wrap"><div
class="cm_replymail_content_1455098788_wrapper" style="color: rgb(0, 0,
0);">On Wed, Feb 10, 2016 at 9:35 am, Samuel <samuelrivas@gmail.com>
wrote:<br> <div id="cm_replymail_content_1455098788"
style="overflow: visible;"><blockquote style="color: #303B40;">>>
What would be the best direction or tools to start
with?<br>><br>><br>> I would start by writing a tensorflow program
as something you can talk to<br>> via a port, should I start today.
Tensorflow networks are configured and<br>> trained in Python, but can
be run everywhere you can call into C. The nice<br>> idea is that you
split network tinkering from actually using the NN you are<br>>
generating.<br><br>I am not aware of existing ML or linear algrebra
libraries in erlang<br>that can be used to quick start an ML project, but
just piping into<br>tensorflow (or any other existing library/framework)
isn't really<br>doing ML with erlang, is it? You can as well just use
tensorflow<br>directly.<br><br>Unless the problem to solve is orchestrating
a big, distributed system<br>that has some ML components in it; then doing
the orchestration in<br>Erlang that way might be a good idea.<br><br>It
still could be an interesting project to create a ML framework in<br>erlang
itself, a quick google reveals some previous works on that, but<br>I
haven't gone through any of them, so I'll let the Theepan do
the<br>research
:)<br>_______________________________________________<br>erlang-questions
mailing
list<br>erlang-questions@erlang.org<br>http://erlang.org/mailman/listinfo/erlang-questions<br></blockquote></div></div>
</div> </div>