a question: can neural networks be made to do this?

sajeev batra batra at tigger.cs.colorado.edu
Wed Jul 15 19:49:50 EST 1992

In article <1992Jul14.181707.3007 at athena.mit.edu> mlevin at presto.cs.tufts.edu (Mike Levin) writes:
>    I have a question about applying neural nets to a certain problem.
>Suppose I have a certain generative algorithm, that takes a small
>string as input, and produces a two-dimensional image (array of color
>indeces) as output. The L-systems are an example of such an algorithm,
>and so are fractal functions when plotted.  Suppose also that
>producing an image from such a seed is simple (though computationally
>intensive), but finding a seed to produce a given image is very
>difficult to do (for a human being). Is it possible to train up a
>neural network bu giving it an image, having it guess at a seed, and
>then giving it the correct seed to let it adjust its weights. The hope
>then is that after a while the net's guesses will become good, and it
>can be used to derive seeds for arbitrary images. There is an infinite
>supply of training material, because there is an infinite amount of
>randomly-chosedn seeds to produce images.
>    So, does anyone have any suggestions about this? Is it feasable to
>feed a network an image as input? What do I need to do to make it
>return legal seeds as guesses? Are there any public domain neural net
>packages that may be used to try this? How does the size (number of
>nodes, layers, etc.) depend on the difficulty of the problem? Please
>send me any info on this you may have at mlevin at presto.cs.tufts.edu.
>Mike Levin

Already, there exist numerous image reconstruction algorithms.  Seeds are
constructed into images.  Also, there exist many image compression 
algorithms; the given image is reduced into a seed. I guess you would 
like to use a neural net to compress the image into a seed.  The image is 
presented as input to the net and the output is a compressed "seed."

Yes, many papers exist on this difficult problem.  An introductory paper
that discusses neural nets with applications to image processing (among
other things) is by Lippmann, "An Introduction to Computing with Neural 
Nets", IEEE ASSP Magazine, April 1987, 4-22.  Perhaps, someone else has
some other suggestions?  Also, I am not sure if neural nets are the
best approach to this problem.  Perhaps, you can post to the newsgroup

good luck.

More information about the Comp-bio mailing list