Mike Tintner writes:
Yes. Thanks. I had seen that. (And I still have to fully understand his
system). But my question remains: where did you get your information about
his system's FAILURES to recognize basic types?
?
I never said anything about failures. You asked
whether he has yet made the transition from being able to recognise a "dog"
to being able to recognize an "animal."
I said:
I'm fairly certain the answer is no -- in fact as far as I know there has
not even been a demonstration of HTM doing dog recognition (or anything
similarly complex). I believe Hawkins would likely say that the
"conceptual" regularities for an animal concept can and will be discovered
by HTM. But no such demonstration has yet been made.
I do not consider the contrived stick figure software to be successful
"dog recognition". You might disagree, I suppose.
HTM has not (to my knowledge) "failed" to do complex and impressive
abstract categorization tasks like dog or animal recognition, it just
hasn't demonstrated success at doing so.
-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=231415&user_secret=fabd7936
