[extropy-chat] Greetings

[Neil H.]

On 12/9/05, Derek Zahn <DerekZahn at msn.com> wrote:
>
> Hi Neil!
>
> The field has very likely moved beyond my research topic by this point (I
> haven't been following it for 10 years or so).  The concept was to
> experiment with evolvable languages for expressing structure (for example,
> the structure of neural networks or other parallel processing networks with
> semi-uniform architectures), in particular where the structures unfold from
> a "developmental" process.  The hope was that atomic operations on
> representations of developmental processes would have the ability to cause
> both coarse and fine alterations in structure and thus function and with an
> appropriate representation would thus be fruitful for either automatic
> "genetic algorithm" style exporation of the space of possible structures, or
> for direct "intelligent design" by a person.
>

Ah, interesting. I used to be obsessed with genetic/evolutionary algorithms
myself, but ultimately shifted to other areas.

Good luck with your research!  What are you working on?
>

Thanks! I'm just starting the 2nd year of my PhD program and so I'm still
searching for a good thesis topic, but in general my department deals with
interdisciplinary aspects of neuroscience and computer science. I'm in a
computer vision lab in the department and not doing too much with the neuro
end of things, but I'm hoping to somehow integrate some neuro or
psychophysical work later on. I'm currently working on various aspects of
visual object recognition and the visual correspondence problem. I'm also
working on applications of spectral graph theory to object recognition.

-- Neil
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20051213/1cc31a05/attachment.html>