Comparison and Combination of State-of-the-art Techniques for Handwritten Character Recognition: Topping the MNIST Benchmark
arXiv:0710.2231
Abstract
Although the recognition of isolated handwritten digits has been a research topic for many years, it continues to be of interest for the research community and for commercial applications. We show that despite the maturity of the field, different approaches still deliver results that vary enough to allow improvements by using their combination. We do so by choosing four well-motivated state-of-the-art recognition systems for which results on the standard MNIST benchmark are available. When comparing the errors made, we observe that the errors made differ between all four systems, suggesting the use of classifier combination. We then determine the error rate of a hypothetical system that combines the output of the four systems. The result obtained in this manner is an error rate of 0.35% on the MNIST data, the best result published so far. We furthermore discuss the statistical significance of the combined result and of the results of the individual classifiers.
arXiv comment13 pages
Cited by in corpus (4)
- The Effects of Hyperparameters on SGD Training of Neural Networks
- Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
- SIRe-Networks: Convolutional Neural Networks Architectural Extension for Information Preservation via Skip/Residual Connections and Interlaced Auto-Encoders
- Towards A Measure Of General Machine Intelligence