Artigo Acesso aberto Revisado por pares

Deep, Big, Simple Neural Nets for Handwritten Digit Recognition

2010; The MIT Press; Volume: 22; Issue: 12 Linguagem: Inglês

10.1162/neco_a_00052

ISSN

1530-888X

Autores

Dan Claudiu Cireşan, Ueli Meier, Luca Maria Gambardella, Jürgen Schmidhuber,

Tópico(s)

Vehicle License Plate Recognition

Resumo

Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning.

Referência(s)