From: Petter Wingren-Rasmussen (petterwr@gmail.com)
Date: Mon Feb 23 2009 - 22:49:51 MST
On Sun, Feb 22, 2009 at 8:49 PM, Johnicholas Hines <
johnicholas.hines@gmail.com> wrote:
>
> If I understand correctly, you propose using evolution or something
> similar, inside a sequence of synthetic environments. The environments
> are designed to simultaneously select for friendly emotions and useful
> capabilities. The sequence of environments can be considered one
> environment with a sequential structure.
Not necessarily sequential, could be branching too. Otherwise you got it and
expressed it more elegantly than me too.
1. Genetic algorithms (along with brute-force search and other generic
> learning strategies) produce holographic output. By "holographic" I
> mean every part relates to every other part; it is not modular the way
> humans normally design and understand things.
Could still be modular, if you find an efficient way to connect different
units from different branches in a network.
I think this might work out pretty similarly to the human brain.
I dont have any clear idea of how to make them communicate as efficiently as
the parts of the human brain does though.
Thanks a lot for the rest of your text, Johnicholas. Inspiring!
IŽll read up a bit and get back here.
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:04 MDT