High-Performance Neural Networks for Visual Object Classification
Artificial Intelligence
2011-02-02 v1 Neural and Evolutionary Computing
Abstract
We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates of 2.53%, 19.51%, 0.35%, respectively. Deep nets trained by simple back-propagation perform better than more shallow ones. Learning is surprisingly rapid. NORB is completely trained within five epochs. Test error rates on MNIST drop to 2.42%, 0.97% and 0.48% after 1, 3 and 17 epochs, respectively.
Cite
@article{arxiv.1102.0183,
title = {High-Performance Neural Networks for Visual Object Classification},
author = {Dan C. Cireşan and Ueli Meier and Jonathan Masci and Luca M. Gambardella and Jürgen Schmidhuber},
journal= {arXiv preprint arXiv:1102.0183},
year = {2011}
}
Comments
12 pages, 2 figures, 5 tables