[ml] Wednesday 12/1/2010 @ 7:30pm: ICA

Mike Schachter mike at mindmech.com
Wed Dec 1 08:35:41 UTC 2010


Also, here's a 1995 paper describing how to implement ICA
in neural networks, the so-called "infomax" algorithm:

http://www.mitpressjournals.org/doi/abs/10.1162/neco.1995.7.6.1129

Since neural networks are super fucking awesome, I'll
probably focus on that particular ICA implementation. If
you don't have journal access, here's a somebody's
informative presentation on it:

http://www.cis.hut.fi/Opinnot/T-61.184/s00/salojarvi.ps

  mike




On Wed, Dec 1, 2010 at 12:06 AM, Mike Schachter <mike at mindmech.com> wrote:

> One of the things that inspired this talk on ICA was it's use for
> detecting people's heart rates via webcam, described in a
> paper here:
>
> http://www.opticsinfobase.org/abstract.cfm?URI=oe-18-10-10762
>
> I'll definitely touch on the paper during the ICA overview.
>
>   mike
>
>
>
>
> On Tue, Nov 30, 2010 at 1:08 PM, Mike Schachter <mike at mindmech.com> wrote:
>
>> Hi everyone!
>>
>> Tomorrow we're having a presenation on Indepenent Component
>> Analysis. I'll give a brief background on what ICA is and what it
>> can be used for, then Neuroscientist and felllow Noisebridger
>> Todd Anderson will talk about what he uses it for.
>>
>> See you then!
>>
>>  mike
>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.noisebridge.net/pipermail/ml/attachments/20101201/00bf9c29/attachment-0003.html>


More information about the ml mailing list