Mitchell Timin wrote:
> My motivation waxes and wanes.  Recently, it has waned again.  It will 
> probably
> come back eventually, at least it always has in the past.  So I'm not 
> doing any
> actual programming right now.  I still check our website stats, and I 
> still
> look over comp.ai.neural-nets and comp.ai.genetic, and make the occasional
> post.  Of course I read any messages that come thru this mailing list, but
> lately I'm the only poster.
>
> I'm still available to assist anyone who wants to do something.  Would 
> anyone
> like to prepare something to be published on our SF pages or home pages?
>
> I took a brief look at Dave's program, wbreduce.c, and it looks good.  It 
> could
> be published along with my waybak.c, but the latter needs changes to the
> comments, which are still mostly using the vocabulary of 4Play.c.  If 
> anyone
> would be willing to edit the comments in that project they can get their 
> name
> as a co-author.
>

I started working up the image for the waybak VizANN earlier this week. Once 
I have that, I can start on the simulator coding.

I will be on "vacation" next week (I will be programming at home instead of 
at the office.) I plan to spend some time on ANNEvolve.

Shortly after writing wbreduce and observing the results, I started reading 
"The Three-Pound Enigma". The book contains an interview with Crick (a few 
months before he died) and Koch. Crick mentioned that his transition from 
biochemistry to consciousness studies began with a visit to Tomaso Poggio, 
who was studying dendritic spines at the time. The book notes that there is 
some evidence the spines are related to learning.

I visualized a crude analogy where the connections eliminated by wbreduce 
were similar to the spines that fade away when learning 'settles'. If 
wbreduce ran periodically during the 'runmany' script, it would speed up the 
processing (if the connection count were actually reduced), making 'better' 
use of CPU time.

Likewise, connections could be restored (as spines grow) as a part of the 
reverse process, nudging the ANN into new behavior.

I haven't given it a whole lot of thought but I was thinking about the 
possibility of having 'fuller-than-fully-connected' ANNs (to correspond to 
burgeoning dendritic spine growth.) Obviously, multiple connections with 
simple weights would not be useful - superposition would collapse the 
connections into a single weight. No, something non-linear would have to be 
introduced.

Just talking out loud....Maybe there's a good idea in there?

I'll be posting occasionally during the next week.

Dave 


-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys -- and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV

Reply via email to