论文信息 - Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs

Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs

The competitive MNIST handwritten digit recognition benchmark has a long history of broken records since 1998. The most recent substantial improvement by others dates back 7 years (error rate 0.4%) . Recently we were able to significantly improve this result, using graphics cards to greatly speed up training of simple but deep MLPs, which achieved 0.35%, outperforming all the previous more complex methods. Here we report another substantial improvement: 0.31% obtained using a committee of MLPs.

[1] Leo Breiman,et al. Bagging Predictors , 1996, Machine Learning.

[2] Radford M. Neal. Pattern Recognition and Machine Learning , 2007, Technometrics.

[3] Luca Maria Gambardella,et al. Deep, Big, Simple Neural Nets for Handwritten Digit Recognition , 2010, Neural Computation.

[4] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[5] Marc'Aurelio Ranzato,et al. Efficient Learning of Sparse Representations with an Energy-Based Model , 2006, NIPS.

[6] Patrice Y. Simard,et al. Combining Multiple Classifiers for Faster Optical Character Recognition , 2006, Document Analysis Systems.

[7] Yoshua Bengio,et al. Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[8] Patrice Y. Simard,et al. Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[9] Marc'Aurelio Ranzato,et al. Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[10] P. Werbos,et al. Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[11] Yann LeCun,et al. Une procedure d'apprentissage pour reseau a seuil asymmetrique (A learning scheme for asymmetric threshold networks) , 1985 .