Handwritten Digit Recognition: A Neural Network Demo
暂无分享,去创建一个
A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen's self-organizing feature map. The purpose of this project was to introduce neural networks through a relatively easy-to-understand application to the general public. This paper describes several techniques used for preprocessing the handwritten digits, as well as a number of ways in which neural networks were used for the recognition task. Whereas the main goal was a purely educational one, a moderate recognition rate of 98% was reached on a test set.
[1] Teuvo Kohonen,et al. Self-Organizing Maps , 2010 .
[2] Widrow,et al. DARPA Neural Network Stdy , 1988 .
[3] Lakhmi C. Jain,et al. KNOWLEDGE-BASED INTELLIGENT TECHNIQUES in CHARACTER RECOGNITION , 1999 .
[4] Harris Drucker,et al. Comparison of learning algorithms for handwritten digit recognition , 1995 .