A programmable optoelectronic neural network architecture is examined that has been optimized to make routing decisions in both crossbar and banyan packet switch fabrics. Experimental results are presented that demonstrate a high tolerance to both noise and component inconsistencies.
© 2003 Optical Society of America
K. J. Symington, Y. Randle, A. J. Waddie, M. R. Taghizadeh, and J. F. Snowdon, "RM3A programmable optoelectronic neural network packet switch scheduler," in Optics in Computing, A. Sawchuk, ed., Vol. 90 of OSA Trends in Optics and Photonics (Optical Society of America, 2003), paper PD4.
References are not available for this paper.