Bruno,
There are a lot of amazing theorems in that field. For example the
theorem of Blum and Blum, which says that there is something
infinitely (even non computably) more clever (in learning) than any
machine: a couple of (independent) machines!
Learning machines exist, and the theory
On 31 Dec 2009, at 11:58, Telmo Menezes wrote:
Bruno,
There are a lot of amazing theorems in that field. For example the
theorem of Blum and Blum, which says that there is something
infinitely (even non computably) more clever (in learning) than any
machine: a couple of (independent)
Thanks Bruno!
A great 2010 to you and everyone on the list.
On Thu, Dec 31, 2009 at 7:09 PM, Bruno Marchal marc...@ulb.ac.be wrote:
On 31 Dec 2009, at 11:58, Telmo Menezes wrote:
Bruno,
There are a lot of amazing theorems in that field. For example the
theorem of Blum and Blum, which says
John,
On 29 Dec 2009, at 20:57, John Mikes wrote:
excuse me if I suggest some circularity in you reply.
You are welcome.
A learning machine is by def. learning SOMETHING
Yes. Usually a total computable function, or a mechanically generable
set, or things represented by those things.
On 27 Dec 2009, at 23:16, russell standish wrote:
On Sun, Dec 27, 2009 at 10:54:53AM -0500, John Mikes wrote:
I wonder if a 'robot' can produce a noch nie dagewesen (Ger. for
brand
new) unrelated idea?
I do know Hod Lipson from the ALife community, but am not familiar
with this
Bruno,
excuse me if I suggest some circularity in you reply. A learning machine
is by def. learning SOMETHING and that SOMETHING comes from its inside, if
we do not specify an 'outside' it may explore (which would not be *learning*,
rather *exploring* - a quite different ballgame - maybe followed
Russell,
I made my WEB-acquaintance with Hod - his interview-picture with his
students reminded me of my then Cornelian son and friends, (before he was
for 17 yrs in IBM's development)
and saw that the 'inductive' you mention is still based on the already
known(?) elements. The creative is
On Dec 28, 8:29 am, Brent Meeker meeke...@dslextreme.com wrote:
Actually we've used theories that were elegant and predictive but we didn't
understand for a long time - it's called engineering.
Brent
Yes indeed! Remember my thread challenging Bayesian Induction as the
basis for science?
This article made me think immediately about Colin, and his very own
proof that this is not possible. Of course I'm sure he is talking
about something completely different :).
http://www.wired.com/wiredscience/2009/12/download-robot-scientist/
Cheers
--
Russell, - interesting idea and I appreciate it within the line I don't
really appreciate.
I pretend to be one of the 'research oriented' - I am reluctant of saying
scientist - which may fit into a robot-performed activity.
In the commi administration I had a pretty free hand to come up with ideas
On Sun, Dec 27, 2009 at 10:54:53AM -0500, John Mikes wrote:
I wonder if a 'robot' can produce a noch nie dagewesen (Ger. for brand
new) unrelated idea?
I do know Hod Lipson from the ALife community, but am not familiar
with this particular piece of research. From the WIRED article, I
11 matches
Mail list logo