Journal of Artificial Intelligence, Machine Learning and Soft Computing

Abstract

This paper chronicles the development of an artificial neural network designed to recognize handwritten digits. The neural network described here is not a general-purpose neural network, and it's not some kind of a neural network workbench. Rather, we will focus on one very specific neural network (a five-layer convolutional neural network) built for one very specific purpose (to recognize handwritten digits). One of our goals here was to reproduce the accuracy achieved by Dr. LeCun, who was able to train his neural network to achieve 99.18% accuracy (i.e., an error rate of only 0.82%). This error rate served as a type of "benchmark", guiding our work.

Keywords:  Digit Recognition, Neural Networks, Handwritten Digit Recognition, Artificial Neural Networks