On 9/6/06, Fredrik Heintz <[EMAIL PROTECTED]> wrote:
> And inductive approaches have problems with overfitting and thereby
> lack of generality. They can find a pattern that very closely match
> your examples, but if you give it a radically new example it will
> utherly fail to generalize. Therefore the approach is more sensitive
> to what test cases you choose, and what attributes you classify on. I
> would like to see different approaches as complementary. Use each
> method where it works well and do not try to squeeze everything in one
> mold.
>
> But maybe I miss your point.
> And inductive approaches have problems with overfitting and thereby
> lack of generality. They can find a pattern that very closely match
> your examples, but if you give it a radically new example it will
> utherly fail to generalize. Therefore the approach is more sensitive
> to what test cases you choose, and what attributes you classify on. I
> would like to see different approaches as complementary. Use each
> method where it works well and do not try to squeeze everything in one
> mold.
>
> But maybe I miss your point.
The problem you're pointing out is justified, but it can be resolved by fuzzy logic or probabilities. For example, a "face" may be defined by 10 features, each with probability values linked to it. Then even when some features fail to match, recognition is still OK.
The "massive parallelism" of NN is not needed.
> I have nothing against GOFAI and my point has nothing to do with NN/GA
> being more inspired by biology (neither that you should consider it
> more nor less interesting because it has analogies in biology). As a
> matter of fact, I like the symbolic route and believe it is necessary
> being more inspired by biology (neither that you should consider it
> more nor less interesting because it has analogies in biology). As a
> matter of fact, I like the symbolic route and believe it is necessary
Indeed, I think "GOFAI++" is the right approach, meaning GOFAI extended with new insights from fuzzy/probabilistic logic, and new methods in symbolic machine learning. But not a clean break from GOFAI.
YKY
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
