[viergroupie]

I think you're misunderstanding the role of "neural networks" in academia. NIPS has a lot of value to the machine learning and AI communities but, beyond vague inspiration, it has almost no connections to neuroscience. There is a substantial body of work in computational modeling of neuronal behavior, but this stuff is much messier (PDEs with biologically determined constants) and limited in scope than the papers that appear at NIPS.

edit: Relevant conferences in computational neuroscience -

* http://cosyne.org/c/index.php?title=Cosyne_09

* http://www.cnsorg.org/2009/

* http://icms.org.uk/workshops/mathneuro2009

[robg]

Sorry, but the CS approaches have much to share with neuroscience even in these very early (and messy) days.

Machine learning is now used to analyze neuroimaging data and predict behavioral responses.

http://polyn.com/struct/NormEtal06_TICS.pdf

I also know of one group merging their intelligent tutors with fMRI data to predict types of confusion and offer better suggestions.

[DaniFong]

I don't really know much about neuroscience proper. I tend to look at the simplified artificial models and synthesize what might be possible, rather than look at all at the biology.