I thought the whole "we can guess what you're thinking from an MRI" thing was BS, along the lines: take a small set of photos, image people's brains as they are looking at these pictures, to map to some low-dimensional vector of "brain activity". Then show them some of these (in sample!) pictures, measure the vector of activity and predict back what they were looking at.
Happy to be corrected. But if that's right then this... does the BS thing in a potentially less intrusive way?
How is that BS? If the technique works, you can grow your sample of imaged brains and viewed images ad infinitum, and then why wouldn't I be able to tell what random thing any random person is looking at?
1. Yes, that is generally what those studies did. 2. Th studies are not BS, the popular press description of those studies is BS.
The patterns and locations of activations might be predictive within a sample of images, but cannot discriminate in other samples. The temporal and spatial resolution is too low.
Great. Do you have to hand an accessible non-BS description of one of those?
I have no biology background, but one ML PoV in-depth description I read of these sounded indistinguishable from BS.