Better digit recognition with a committee of simple Neural Nets

摘要：

We present a new method to train the members of a committee of one-hidden-layer neural nets. Instead of training various nets on subsets of the training data we preprocess the training data for each individual model such that the corresponding errors are decorrelated. On the MNIST digit recognition benchmark set we obtain a recognition error rate of 0.39%, using a committee of 25 one-hidden-layer neural nets, which is on par with state-of-the-art recognition rates of more complicated systems.

作者: Ueli Meier Dan Claudiu Ciresan Luca Maria Gambardella Jürgen Schmidhuber

作者单位: IDSIA USI, SUPSI 6928 Manno-Lugano, Switzerland

会议类型: 国际会议

会议名称: 第11届文档分析与识别国际会议(ICDAR)

会议地点: 北京

会议语种:英文

页码: 1250-1254

在线出版日期: 2011-09-01（万方平台首次上网日期，不代表论文的发表时间）