Neural Network for Recognition of Handwritten Digits

Mike O'Neill

Rate me:

4.97/5 (240 votes)

5 Dec 200668 min read

2.1M

57.5K

571

A convolutional neural network achieves 99.26% accuracy on a modified NIST database of hand-written digits.

Revisions

Compare	Revision	Minor	Date	Status	Editor
	1 - publicly available	No	5-Dec-06 8:38	Available	Smitha Nishant

License

This article has no explicit license attached to it but may contain usage terms in the article text or the download files themselves. If in doubt please contact the author via the discussion board below.

A list of licenses authors might use can be found here

Written By

Mike O'Neill

United States

Mike O'Neill is a patent attorney in Southern California, where he specializes in computer and software-related patents. He programs as a hobby, and in a vain attempt to keep up with and understand the technology of his clients.

Neural Network for Recognition of Handwritten Digits

Revisions

License

Comments and Discussions