Deep learning with convolutional neural networks for brain mapping from EEG

Re:Deep learning with convolutional neural networks for brai... by rosser on Sunday April 30, 2017 @03:01PM (#14233235)

There is something so deliciously meta about this. FMRI scans might also be a very interesting place to play with CNNs.

[ Parent | on HN ]

Re:Deep learning with convolutional neural networks for brai... by nullc on Sunday April 30, 2017 @05:12PM (#14233878)

FMRI has very poor temporal resolution and moderately poor spatial resolution-- it's like trying to figure out the workings of your computer by using a meat thermometer.

[ Parent | on HN ]

Re:Deep learning with convolutional neural networks for brai... by chrisfosterelli on Sunday April 30, 2017 @06:25PM (#14234204)

While yes fMRI lacks temporal resolution, the spatial resolution is way better compared to EEG. You also have the benefit of 3D spatial data while EEG only provides 2D data from the scalp. If temporal resolution is important, MEG can be used and has better spatial resolution than EEG.

Generally, EEG's benefit is that it's cheaper (either in terms of data collection or for showing your method has the potential to be commoditized).

[ Parent | on HN ]

Re:Deep learning with convolutional neural networks for brai... by return0 on Sunday April 30, 2017 @05:25PM (#14233935)

Plus an fMRI machine is not easy to fit on your desk or carry with you.

[ Parent | on HN ]

Re:Deep learning with convolutional neural networks for brai... by jacquesm on Sunday April 30, 2017 @07:53PM (#14234603)

A portable fMRI machine... that's the stuff of dreams. For sure that would change the world for the better but I really don't see how you would even begin to tackle that.

[ Parent | on HN ]

Re:Deep learning with convolutional neural networks for brai... by namlem on Tuesday May 02, 2017 @12:25PM (#14247774)

Room temperature superconductors would certainly help a lot.

[ Parent | on HN ]

Re:Deep learning with convolutional neural networks for brai... by return0 on Sunday April 30, 2017 @08:11PM (#14234665)

I suppose with a few years of weightlifting, it can become portable ...

[ Parent | on HN ]

Re:Deep learning with convolutional neural networks for brai... by chrisfosterelli on Monday May 01, 2017 @02:12PM (#14239977)

I suppose, if you can also weightlift a magnetically & RF shielded room with you :P

[ Parent | on HN ]

Re:Deep learning with convolutional neural networks for brai... by blackRust on Sunday April 30, 2017 @04:20PM (#14233616)

There's a decent amount of work that's been done already in this area, see [1] and follow up work by the same authors for a good example. While the approach is "cool" there are still many unanswered questions of what exactly it tells us about the brain. See [2], a critical review of [1], for an indication of what I mean.

- [1] http://www.jneurosci.org/content/35/27/10005 - [2] http://www.jneurosci.org/content/35/48/15769

[ Parent | on HN ]