But what is a neural network? | Deep learning chapter 1

Further reading 2

What improved when a game agent got better? →A rising score might reflect a better network, deeper search or a loophole. Trace what the agent observes, what it tries and why the resulting move earns a reward.This video helps answer · Can a network evolve its own wiring?How far is next-token prediction from answering a person? →Separate three questions: how an input becomes a representation, how training changes a network and how a capable text predictor becomes an assistant. An explanation at one level does not settle the others.This video helps answer · What does attention add to layered activations?

Caption notes

A network for handwritten digits turns pixels into activations using learned weights, biases and nonlinearities. This chapter explains the architecture before training.

Original passages · 5

Whether or not this is what our final network actually does is another question

But what is a neural network? | Deep learning chapter 1 · ▶ 7:40–7:44

the bias tells you how high the weighted sum needs to be

But what is a neural network? | Deep learning chapter 1 · ▶ 11:27–11:35

this makes the relevant code both a lot simpler and a lot faster

But what is a neural network? | Deep learning chapter 1 · ▶ 15:05–15:14

the heart of the network as an information processing mechanism

But what is a neural network? | Deep learning chapter 1 · ▶ 4:39–4:43

the entire network is just a function

But what is a neural network? | Deep learning chapter 1 · ▶ 15:39–15:43

Hacker News comments

View original on HN ↗