Hacker News new | past | comments | ask | show | jobs | submit login

Maybe I'm missing something, but I don't see how this correlation shows that the mapping is semantic and not, say, grammatical, syntactic, or structural in some way.



There is deep discussion of that topic in the paper. Attention, audio processing, and lexical layers are brought to the forefront of their discussion.

To quote the authors: ”We propose that deep neural networks encode a variety of features…”


The correlation doesn't even show a link.

Run GPT on other inputs, run fMRIs on other inputs: call that dataset, (G, F).

Now consider all possible subsets, (g_i, f_i) in (G, F) ...

How many show correlation in their choice of NN property, and their choice of brain property (ie., blood flow)?

My guess: *many*.

This is trivial to refute if you have any sense of the scientific method. Construct the converse hypothesis and test it. They didnt.


It would be interesting to try the same experiment with a syntax parsing / part of speech tagging model and see if it holds.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: