Quick evolve neural network AMD64

Linux specific questions.
sean_vn
Posts: 257
Joined: Aug 06, 2012 8:26

Quick evolve neural network AMD64

Postby sean_vn » Aug 17, 2017 1:50

This is the fastest evolving neural network I have so far:
https://drive.google.com/open?id=0BwsgMLjV0BnhdWltTF9BTGhfa3M

Linux AMD64 only.
sean_vn
Posts: 257
Joined: Aug 06, 2012 8:26

Re: Quick evolve neural network AMD64

Postby sean_vn » Aug 31, 2017 1:39

BasicCoder2
Posts: 2933
Joined: Jan 01, 2009 7:03

Re: Quick evolve neural network AMD64

Postby BasicCoder2 » Aug 31, 2017 2:31

sean_vn wrote:This is the fastest evolving neural network I have so far:

And what does it evolve into?
I have seen examples of evolving behaviors (eg. swimming)
https://www.youtube.com/watch?v=AVU8dza89Mc
Evolving the ability to value a board game.
What is its environment? Its feedback goal?
Any utube video of it in action?
.
sean_vn
Posts: 257
Joined: Aug 06, 2012 8:26

Re: Quick evolve neural network AMD64

Postby sean_vn » Aug 31, 2017 14:59

The code is just infrastructure. It's not embedded in any environment for it to do anything interesting yet.
So the associative memory will just remember a number of <input,target> patterns in arrays that you show it.
The ENet version is somewhat similar but you have to give it all the examples at once, and it can begin to reason out what features in the input result in what features in the output.
The idea is to put the associative memory together with the "smarter" ENet to make some sort of artificial life (alife.)
The difficulty is an alife needs some sort of environment to live in, like a video game or something. That's too troublesome to do at the moment so just to test if a viable alife is possible I will use text prediction as a sort of environment for it to live in.
I have been sort of delaying by translating the code to JavaScript etc. Maybe next week I'll have the text prediction code.
The reason for the truncate code it to use it as a gating function for the associative memory. If the output of the truncate function is zero nothing is written to the associative memory. Any non-zero value is written. That means the smart network can output say 0.9 and with a truncate function with a magnitude diminishing value of 1, the output will be zero and nothing written to the associative memory. If the smart networks outputs 1.1 then 0.1 will be written to memory, if -1.1 then -0.1 will be written. Obviously 0.0 cannot be written to memory using such a scheme, but say 1e-30 could which is near enough.

Return to “Linux”

Who is online

Users browsing this forum: No registered users and 1 guest