---
title: "Flexible, High Performance Convolutional Neural Networks for Image Classification"
authors:
  - "Dan Claudiu Ciresan"
  - "Ueli Meier"
  - "Jonathan Masci"
  - "Luca Maria Gambardella"
  - "Jürgen Schmidhuber"
doi: "10.5591/978-1-57735-516-8/IJCAI11-210"
url: "https://ijcai.org/proceedings/2011/210"
pdf: "https://ijcai.org/proceedings/2011/0210.pdf"
venue: "Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence"
year: 2011
pages: "1237-1241"
track: ""
keywords:
---

# Flexible, High Performance Convolutional Neural Networks for Image Classification

Dan Claudiu Ciresan, Ueli Meier, Jonathan Masci, Luca Maria Gambardella, Jürgen Schmidhuber

*Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence*, pages 1237-1241. DOI: [10.5591/978-1-57735-516-8/IJCAI11-210](https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-210)

## 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.