Hacker News Reader

Comment by rosser | Hacker News Reader

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

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.

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

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.

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

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

Room temperature superconductors would certainly help a lot.

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).

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

Reply on news.ycombinator.com