Le 20/10/2017 à 17:24, Robert Jasiek a écrit :
>  Why, that is easy: test! Modify ONE weight and study its effect on
> ONE aspect of human go theory, such as the occurrance (frequency) of
> independent life. No effect? Increase the modification, test a
> different weight, test a subset of adjacent weights etc. It has been
> possible to study semantics of parts of DNA, e.g., from differences
> related to illnesses. Modifications on the weights is like creating
> causes for illnesses (or improved health).
I really believe you speak of things knowing nothing about. I'm far from
an expert in neural networks but from all that I know about them :

1- It really really unlikely to work
2- It is totally unrelated with DNA
3- It was probably already tried without success
Computer-go mailing list

Reply via email to