140 likes | 513 Views
Handwritten Digits Recognition using Multilayer Perceptron. Yang, Luyu. Motivation. Postal service for sorting mails by the postal code written on the envelop Bank system for processing checks by reading the amount of money using computers. Objective.
E N D
Handwritten Digits Recognition using Multilayer Perceptron Yang, Luyu
Motivation • Postal service for sorting mails by the postal code written on the envelop • Bank system for processing checks by reading the amount of money using computers
Objective • Design artificial neural network for handwritten digits recognition • Develop proposed network using training samples in MNIST database • Achieve good testing result
Details of Architecture Assume each pixel in the digit image is either black or white, which contains 1 bit information. To convert the binary sequence into decimal system {0, 0.1, … ,0.9}, the number of elements should be at least log10(2784), approximately 236.0075. Let the higher precision in MATLAB compensate for the gray edge of stroke. Therefore, 237 neurons are used in the hidden layer to store patterns of training samples.
Details of Architecture In the original 784 pixels, even two samples which are very close under Euclidean norm may represent different digits. So quasi nearest neighbor classifier operates at the output of the hidden layer, where the key features are supposed to be more pronounced.
Performance Comparison with Traditional Classification Methods Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.