Better digit recognition with a committee of simple neural nets

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

48 Scopus citations

Abstract

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. © 2011 IEEE.
Original languageEnglish (US)
Title of host publicationProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Pages1250-1254
Number of pages5
DOIs
StatePublished - Dec 2 2011
Externally publishedYes

Fingerprint

Dive into the research topics of 'Better digit recognition with a committee of simple neural nets'. Together they form a unique fingerprint.

Cite this