24 May 2000 Optical learning neural network with fuzzy controlling
Author Affiliations +
Proceedings Volume 4089, Optics in Computing 2000; (2000) https://doi.org/10.1117/12.386887
Event: 2000 International Topical Meeting on Optics in Computing (OC2000), 2000, Quebec City, Canada
We constructed a learning optical neural network with variable learning coefficient by fuzzy controlling. The system performs learning with 2D optical means for handling images without scanning and pixeling. By the fuzzy controlling theory, the learning coefficient in back- propagation algorithm is adjusted based on the training error and training time. The effectiveness of the system confirmed by the learning experiments of the recognition of three human faces.
© (2000) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Masahiko Mori, Masahiko Mori, Yutaka Yagai, Yutaka Yagai, Xin Lin, Xin Lin, Toyohiko Yatagai, Toyohiko Yatagai, } "Optical learning neural network with fuzzy controlling", Proc. SPIE 4089, Optics in Computing 2000, (24 May 2000); doi: 10.1117/12.386887; https://doi.org/10.1117/12.386887

Back to Top