conference paper

Convolutional Neural Network Committees for Handwritten Character Classification

Dan Claudiu Ciresan^{a b}, Ueli Meier^{a b}, Luca Maria Gambardella^{a b}, Jürgen Schmidhuber^{a b}

^aIDSIA, USI/SUPSI, Manno-Lugano, Switzerland
^bIDSIA, USI, Manno-Lugano, Switzerland

Proceedings of the International Conference on Document Analysis and Recognition Institute of Electrical and Electronics Engineers2011-09-01 538 citations30 references

Looking for the full paper…

Export

Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.

Abstract

In 2010, after many years of stagnation, the MNIST handwriting recognition benchmark record dropped from 0.40% error rate to 0.35%. Here we report 0.27% for a committee of seven deep CNNs trained on graphics cards, narrowing the gap to human performance. We also apply the same architecture to NIST SD 19, a more challenging dataset including lower and upper case letters. A committee of seven CNNs obtains the best results published so far for both NIST digits and NIST letters. The robustness of our method is verified by analyzing 78125 different 7-net committees.

Plain-language summary

AI illustration of the topic of “Convolutional Neural Network Committees for Handwritten Character Classification”

Convolutional Neural Network Committees for Handwritten Character Classification

Abstract

Plain-language summary

Discussion