Deep, Big, Simple Neural Nets for Handwritten Digit Recognition
2010; The MIT Press; Volume: 22; Issue: 12 Linguagem: Inglês
10.1162/neco_a_00052
ISSN1530-888X
AutoresDan Claudiu Cireşan, Ueli Meier, Luca Maria Gambardella, Jürgen Schmidhuber,
Tópico(s)Vehicle License Plate Recognition
ResumoGood 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)