Deep, Big, Simple Neural Nets for Handwritten Digit Recognition

作者：Dan Claudiu Cireşan, Ueli Meier, Luca Maria Gambardella, Jürgen Schmidhuber · 发表于：Neural Computation · 年份：2010 · DOI：10.1162/neco_a_00052 · 被引用次数：1072 · 研究领域：Handwritten Text Recognition Techniques、Image Processing and 3D Reconstruction、Vehicle License Plate Recognition

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.