Ir para o conteúdo
Atlas de IA

Aprendizado profundo

Delegar a engenharia de atributos a camadas empilhadas

OVERVIEW

Todos os conceitos
6
Iniciante
2
Intermediário
3
Especialista
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.