Hi, Paolo,

That's quite close to what I've been thinking about, with no actual doing, so 
far. I'm a computational neuroscientist by training but have been doing 
research neuroimaging informatics for the last 7 years (http://xnat.org, 
http://humanconnectome.org).

There was a talk at OHBM this year (Adam Baker from Oxford, session #2019), 
pointing out that the usual methods for pulling the default mode network out of 
rs-fMRI data assume, to paraphrase roughly, that the correlational structure is 
stationary and that a particular node is involved in only one network. He used 
a hidden Markov model and found (working from fuzzy memory here) that there are 
a few temporally separable default mode networks. I thought this was 
interesting and was wondering what CLA could do with the same problem -- in 
particular, I'm curious whether CLA could predict network dynamics changes (~ 
state transitions in the HMM).

Unfortunately, nobody's funding me to work on this, and I'm frantically 
preparing for a poster in late August, so I'm unlikely to make any progress on 
it in the next few months, but I'm happy to talk about it.

  - Kevin

On Jul 21, 2013, at 2:31 PM, Paulo Mint Labs wrote:

> Hi guys,
>
> I just wanted to say hi to the rest of the community and introduce a bit what 
> am I going to explore.
> First of all, I'm a software engineer and exploring/exploiting neuroimaging 
> for clinical applications. I want to experiment with CLA on resting state 
> fMRI. So I'll begin with a single cortical region's time series (14 minutes 
> resting BOLD signal, about 240 time points), and later bring the rest of the 
> cortical regions. I think CLA should have very interesting applications in 
> this field, besides the 'poetry' of having a cortical algorithm processing 
> cortical activation :)
> Anybody looking into this? Any thoughts? Looking forward to have some nice 
> conversations with you guys!
>
> Cheers,
> Paulo
> _______________________________________________
> nupic mailing list
> [email protected]
> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org


________________________________

The material in this message is private and may contain Protected Healthcare 
Information (PHI). If you are not the intended recipient, be advised that any 
unauthorized use, disclosure, copying or the taking of any action in reliance 
on the contents of this information is strictly prohibited. If you have 
received this email in error, please immediately notify the sender via 
telephone or return mail.

_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org

Reply via email to