Abstract
Recently, Ahumada and Yellott (1) and Maloney (5,6) have presented schemes for training networks designed to reconstruct irregularly sampled retinal images. In these schemes adjustable weighting networks provide compensation for the irregularities in the retinal array and the geometrical distortions in intermediate pathways. This paper presents some ideas relating to the convergence of the training algorithms.
© 1989 Optical Society of America
PDF ArticleMore Like This
Albert J. Ahumada and J. Misha Pavel
WM1 OSA Annual Meeting (FIO) 1989
Albert J. Ahumada and John I. Yellott
THJ3 OSA Annual Meeting (FIO) 1988
Shaoping Bian, Kebin Xu, and Jing Hong
THT26 OSA Annual Meeting (FIO) 1989