alright just for fun: AMA but only about math, will attempt to speed-explain stuff with as few symbols and equations as possible and see what happens
(esp happy to field questions about stuff that seems basic to you and that you feel like you should've gotten a long time ago!)
Conversation
This Tweet was deleted by the Tweet author. Learn more
Most simply:
ML simulates the way neurons activate and connect in the brain. Each neuron takes a set of inputs, does some math to determine its output, and sends that as the input to another set of neurons.
Each node is doing simple lin alg, the complexity arises in the network
2
Replying to
actually i listened to a talk by chris olah once where he started it by specifically saying that neural networks do not behave like neurons and it's not why they work, to the extent that they work
distill.pub/2017/feature-v
"This framing unifies the concepts “neurons” and “combinations of neurons” as “vectors in activation space”."
Interesting, ya from this paper he's an author on they're reframing neurons to vectors.
2