본문으로 건너뛰기
AI 도감

딥러닝

특징 설계를 다층 네트워크에 맡긴다

OVERVIEW

전체 항목
6
입문
2
중급
3
고급
1

The turning point of deep learning was not “more layers” but the discovery that with enough width, data and stable optimisation, the intermediate abstractions grow on their own. This domain starts from a single neuron and works up to backpropagation, convolution, attention and the normalisation tricks that make depth actually trainable.