swarm-support
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Brain protocol


From: Juan J. Merelo
Subject: Re: Brain protocol
Date: Wed, 19 Feb 1997 15:41:19 -0700

OK:

>>>>> "glen" == "glen e p ropella" <address@hidden> writes:

    glen> -(id) think: (id);

Agreen on that. Good on the semantics, good on the syntax. What we
have now, then, is 

@protocol Brain
// Setting
-(id) think: (id);
// Using
-(char*) getBrainID;
@end

        Anything else? Anything missing? What about some kind of
feedback? Once the brain "decides", it should do something with the
results of that decision. That usually happens in neural networks,
where feedforward and training are separated. Besides, that feedback
might be needed to increase fitness.

        What about:
-(void) reThink: (id);    // Could be mull, or feedback.

        See ya!

                                JJ


-- 
address@hidden


reply via email to

[Prev in Thread] Current Thread [Next in Thread]