On 6/29/07, YKY (Yan King Yin) [EMAIL PROTECTED] wrote:
I've talked to John Weng many times before, and I found that his AGI has
some problems but he wasn't very eager to talk about them. For example, it
could only recognize pre-trained objects (eg, a certain doll) but not
general object
On 6/29/07, Lukasz Stafiniak [EMAIL PROTECTED] wrote:
It seems intuitive that bottom-up approach is better at
generalization. HTM is much more sophisticated, conditional
probabilities, and the learning in context of sequences, must really
be helpful. (IHDR can have time-chunking but this is not
In theory, HTM's are not restricted to off-line learning. For some
reason the NuPIC software doesn't allow it ye, primarily because of
implementation issues. One reason is that a HTM module's learning
mechanism presumes a predetermined input alphabet. They're working on
improvements though, iirc.
YKY: I've talked to John Weng many times before, and I found that his AGI has
some problems but he wasn't very eager to talk about them.
MT: Is anyone in AGI eager to talk about their problems? My impression is it's
a universal failing.
YKY: For example, it could only recognize pre-trained
BTW, has HTM been seriously tried at medical images understanding?
-
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=231415user_secret=e9e40a7e
I have followed HTM progress to some extend but have not seen any
medical applications of NuPIC. Or any serious applications for that
matter, unless groups beside Numenta have created an advanced HTM
implementation... To get an idea of current applications you could
check out the (quite shallow)
On 6/29/07, Mike Tintner [EMAIL PROTECTED] wrote:
YKY: I've talked to John Weng many times before, and I found that his AGI
has some problems but he wasn't very eager to talk about them.
MT: Is anyone in AGI eager to talk about their problems? My impression is
it's a universal failing.
From what I've seen so far HTM has only been applied to very trivial
binary images far less complex than medical images or more ordinary
scenes. If they can return reasonable results from camera images in a
way which is invariant to scale, translation and rotation then I'll be
impressed. As I
Bob M:
As I understand it from Numenta's own forums this kind of
invariance is not achievable with the demos which they've produced so
far, although it's an essential characteristic of any general purpose
vision system.
Thanks for info. What then is the feeling/ mood over at Numenta about the
Hi,
I am looking for technical papers and/or code for a simple form
of linguistic pattern recognition, specifically, that for finite
automata.
Its well known that a regular language (a type of formal
language) is in 1-1 correpsondance with a finite state machine
(each finie state machine can
Stefan Pernar wrote:
Now why is that? Cognitive biases could be...
a) ...less fit characteristics of human cognition that did not pose too
big a problem for humanity to make it to the current day (like an
infection prone appendix of the mind - bad but not too bad).
b) ...fitness increasing
11 matches
Mail list logo