Comparison of sinusoidal perceptron with multilayer classical perceptron

Resource type
Authors/contributors
Title
Comparison of sinusoidal perceptron with multilayer classical perceptron
Abstract
A new multi-threshold Perceptron capable of handling both binary and analog input is presented and discussed. The modified Perceptron replaces the sigmoid function with sinusoidal function. A computer program has been developed to simulate behavior of a network utilizing the modified Perceptron. Both XOR and Parity Check problems were solved using a single-layer network utilizing this modified Perceptron. Based on the results obtained from the simulation the modified Perceptron is capable of solving problems (such as XOR) that can not be solved using a single-layer of the classical Perceptron. Also a network utilizing this modified Perceptron requires fewer number of iterations to converge to a solution than that of a multi-layer Perceptron network using back propagation. 1.
Proceedings Title
Applications of Optical Engineering: Proceedings of OE/Midwest '90
Conference Name
Applications of Optical Engineering: Proceedings of OE/Midwest '90
Publisher
International Society for Optics and Photonics
Date
1991/03/01
Volume
1396
Pages
226-236
Citation Key
karimiComparisonSinusoidalPerceptron1991
Accessed
12/17/19, 8:26 PM
Library Catalog
Extra
0 citations (Crossref) [2023-10-31] Citation Key Alias: lens.org/123-003-460-105-676, pop00141
Citation
Karimi, B., Baradaran, T., Ashenayi, K., & Vogh, J. (1991). Comparison of sinusoidal perceptron with multilayer classical perceptron. Applications of Optical Engineering: Proceedings of OE/Midwest ’90, 1396, 226–236. https://doi.org/10.1117/12.25815