On Mar 7, 8:44 pm, casey <jgkjca... from yahoo.com.au> wrote:
> On Mar 8, 8:13 am, "Glen M. Sizemore" <gmsizemo... from yahoo.com> wrote:
>> > Below is a link to a very cool paper. Whether the simple network on page 334
> > is "correct" or not, the flavor of the paper foreshadows, I think, the
> > future of psychology, neuroscience, and artificial intelligence, all rolled
> > into one. The fields are mutually complimentary and, I think, there is no
> > other way.
>> >http://www.pubmedcentral.nih.gov/picrender.fcgi?artid=1284800&blobtyp...>> The other way might be inventing a machine that behaves
> intelligently just as we invented flying machines without
> the need for flapping wings or feathers.
>> When I tried to talk about simple networks you dismissed
> them saying, in essence, you weren't interested as they
> didn't cover conditioning in all its complexity.
>
Unfortunately, current NNs do little more than solve toy problems. In
the recent presentation by Hinton, he mentioned it took him 17 years
to figure out how to properly make something [boltzmann probabilistic
networks] that works significantly faster and better than backprop
networks. And what do his marvelous new networks solve? The
recognition of the numbers 1 to 9 in various distorted forms. 17 more
years down the tubes.
http://www.youtube.com/watch?v=AyzOUbkUf3M
