[squeak-dev] neural net in Squeak?

JOHN VOIKLIS voiklis at gmail.com
Thu Jul 9 22:12:42 UTC 2009


Hi Cam,

I am starting to think that the solution you propose may be best. Most
of the NN models of human category learning look fairly simple, with
3-5 tiers depending on whether they include an attention-learning tier
or name-learning tier in addition to the object-learning tier. I have
found a Python version of the SUSTAIN learning model and I am looking
for a Python version of ALCOVE learning model. With some help from
their original authors, I might be able to port these.

Thanks for your help...if you are willing, I may have a question or
two for you off list.

Thanks again--J

On Thu, Jul 9, 2009 at 5:38 PM, Cameron
Sanders<csanders.personal at functional-analyst.com> wrote:
> John,
>
> A basic synchronous feed-forward model (with back propagation training)
> isn't that hard to write and/or translatefrom another language. I found an
> example written in Python a number of years ago that is only about 50 lines
> of code (for 3-tier net) -- you could rewrite that in Squeak, add a sane
> class hierarchy (that would be mostly empty at first), generalize the
> topology, add the higher level driving methods, and do the basic debugging
> in pretty short-order.
>
> But is that enough? You are interested in human learning, so perhaps you
> actually want asynchronous updates, or something in between. (don't ask... i
> am not certain I can put it to words without spending too much time.)
>
> It is worth considering. I probably will build a limited toolkit in
> smalltalk within a year... but not today.
>
> How large of a net are you wanting to work with? What kind of human
> processing are you wanting to observe? I am thinking about performance with
> these questions. If you want a large network, then one probably needs to use
> an external library.
>
> The over-training warnings are worth paying attention to: do not force the
> system to fit a small data set exactly, and do use too many nodes for the
> problem.
>
> --
> Python is dead-simple to work with. It is very flexible. It is typeless and
> has garbage collection, but uses c-like expressions in many cases. so...
> using FANN with the Python may not be as difficult as you think. I installed
> XCode here on this Mac (my first mac) and python and numerous other
> languages are ready-to-use as a result -- or maybe they were here before,
> but now I have the folding code browser for it. XCode is free from Apple.
>
> Good Luck and please let us know if you find a great turn-key solution!
>
> Cheers,
> Cam
>
>
>



More information about the Squeak-dev mailing list