On 12/18/05, Shane Legg <[EMAIL PROTECTED]> wrote: > > Pei, > > To my mind the key thing with neural networks is that they > are based on large numbers of relatively simple units that > interact in a local way by sending fairly simple messages. > > Of course that's still very broad. A CA could be considered > a neural network according to this description, and indeed > to my mind I don't see much difference between the two. > > Nevertheless, it does rule out many things --- just talk to > somebody who has tried to take a normal algorithm that > does something and turn it into an algorithm that works > on a massively parallel architecture using relatively simple > computations units.
Agree. These are basically what I call "NN ideas" in the meno. NARS has all these properties, but on a technical level, I don't think I can call it a "neural network". > As I see it neural networks are more a paradigm of computation > rather than any specific AI method or technology. This means > that talking about them in general is difficult. There is clearly some "family resemblance" among various types of NN, but it is hard to capture. This is what I'm after, so my question is not about the cutting-edge NN research, but about what make a system to be labeled as a "neural network". > What you seem to be criticising in your memo is what I'd call > "feed forward neural networks". I see what you mean, though in the memo I didn't rule out feedback. Pei > > Shane > > > > ________________________________ > To unsubscribe, change your address, or temporarily deactivate your > subscription, please go to > http://v2.listbox.com/member/[EMAIL PROTECTED] > > ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
