RIS ID
13026
Abstract
This paper presents the application of a new class of convolutional neural networks based on the mechanism of shunting inhibition for handwritten digit recognition. With a three layer network architecture and the use of shunting inhibitory neurons as information processing elements, the network consists of 1926 trainable parameters which are adapted by a first-order gradient training algorithm derived from Rprop, Quickprop, and SuperSAB. Trained on a dataset of 10,000 samples and evaluated on the entire test set of the MNIST database, these networks achieve classification accuracies above 93% with the best performance obtained from those networks with partial connection schemes.
Publication Details
F. Tivive & A. Bouzerdoum, "Handwritten digit recognition based on shunting inhibitory convolutional neural networks", in Workshop on Learning Algorithms for Pattern Recognition in Conjuction with the 18th Australian Joint Conference on Artificial Intelligence (AI'05), 2005, pp. 72-77.