Learning algorithms for classification: A comparison on handwritten digit recognition
Yann LeCun, L. D. Jackel, Léon Bottou et al. · 1995
This paper compares the performance of several classifier algorithms on a standard database of handwritten digits. We consider not only raw accuracy, but also training time, recognition time, and memory requirements. When available, we report measurements of the fraction of patterns that must be rejected so that the remaining patterns have misclassification rates less than a given threshold. 1. Introduction Great strides have been achieved in pattern recognition in recent years. Particularly striking results have been attained in the area of handwritten digit recognition. This rapid progress has resulted from a combination of a number of developments including the proliferation of powerful, inexpensive computers, the invention of new algorithms that take advantage of these computers, and the availability of large databases of characters that can be used for training and testing. At AT&T Bell Laboratories we have developed a suite of classifier algorithms. In this paper we contrast th...
Cited by 423 works.
Authors
- Yann LeCun
- L. D. Jackel
- Léon Bottou
- Corinna Cortes
- John S. Denker
- Harris Drucker
- Isabelle Guyon
- Urs Müller
- Eduard Säckinger
- Patrice Simard
- Vladimir N. Vapnik
References
- Pattern classification and scene analysis
- A training algorithm for optimal margin classifiers
- Handwritten Digit Recognition with a Back-Propagation Network
- The Strength of Weak Learnability
- Efficient Pattern Recognition Using a New Transformation Distance
- BOOSTING PERFORMANCE IN NEURAL NETWORKS
- Comparing different neural network architectures for classifying handwritten digits
- Articular cartilage: degeneration and osteoarthritis, repair, regeneration, and transplantation.
- A system for high-speed pattern recognition and image analysis
- Achieving supercomputer performane for neural net simulation with an array of digital signal processors