Concepedia

The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]

IEEE Signal Processing Magazine · 2012 · 4.4K citations · 7 references

Abstract

In this issue, “Best of the Web” presents the modified National Institute of Standards and Technology (MNIST) resources, consisting of a collection of handwritten digit images used extensively in optical character recognition and machine learning research.

References

7

Gradient-based learning applied to document recognition

Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 56.5K citations · Full text

Engineering, Machine Learning, Multilayer Neural Networks +17

Best practices for convolutional neural networks applied to visual document analysis

P. Simard, Don Steinkraus, John Platt · 2005 · 2.8K citations

Convolutional Neural Network, Engineering, Machine Learning +18

What is the best multi-stage architecture for object recognition?

Kevin Jarrett, Koray Kavukcuoglu, M. Ranzato et al. · 2009 · 2.2K citations

Best Multi-stage Architecture, Convolutional Neural Network, Feature Extraction Stages +18

Flexible, high performance convolutional neural networks for image classification

Dan Cireşan, Ueli Meier, Jonathan Masci et al. · International Joint Conference on Artificial Intelligence · 2011 · 1.2K citations

Convolutional Neural Network, Engineering, Machine Learning +18

Convolutional Neural Network Committees for Handwritten Character Classification

Dan Claudiu Cireşan, Ueli Meier, Luca Maria Gambardella et al. · 2011 · 536 citations

Convolutional Neural Network, Engineering, Machine Learning +16