Deep, Big, Simple Neural Nets for Handwritten Digit Recognition

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

Neural Computation（2010）

引用 696|浏览4

暂无评分

摘要

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.

查看译文

关键词

training set deformations,gpu graphics processing unit,bp back-propagation.,mlp multilayer perceptron,mnist 1,nn neural network,multi layer perceptron,neural network,back propagation,multilayer perceptron,neural net,error rate

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要