factual

Brain-data-augmented training as auxiliary loss

An idea (originally from a Gwern blog post) is to train AI not only to predict labels but also, as an auxiliary loss, to predict the human neural activity pattern evoked by the stimulus, potentially sculpting the network to represent information the way the brain does, improving generalization and robustness (e.g. to adversarial examples) — limited today only by the difficulty of collecting brain-activity data, not by principle.

factualpending

Speaker

Adam Marblestone

Evidence Quote

“It is harder to generate lots and lots of brain activity patterns that correspond to things that you want to train the AI to do. But again, this is just a technological limitation of neuroscience. If every iPhone was also a brain scanner, you would not have this problem and we would be training AI with the brain signals.”

Source

Adam Marblestone – AI is missing something fundamental about the brain— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:32:22 AM

Your notes

Loading notes...