Hacker News new | ask | show | jobs
by echoangle 538 days ago
Isn’t that exactly what we’re currently doing? The problem is that doing this few billion times for every token seems to be harder than just powering some actual neurons with sugar.
1 comments

I think the algorithm is pretty different though I'm not expert on the stuff. I don't think the brain processes look like matrix multiplication.
The algorithm (of a neural network) is simulating connections between nodes with specific weights and an activation function. This idea was derived from the way neurons are thought to work.