Better Digit Recognition with a Committee of Simple Neural Nets
Document Analysis and Recognition（2011）
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 decor related. 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.
更多查看译文
关键词
mnist digit recognition benchmark,training data,various net,recognition error rate,individual model,complicated system,simple neural nets,corresponding error,one-hidden-layer neural net,new method,state-of-the-art recognition rate,better digit recognition,neural networks,text analysis,shearing,set theory,neural nets,mnist,pattern recognition,benchmark testing,learning artificial intelligence
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