Abstract
Objects are usually stored in neural networks as sets of weights on synapses that multiply input values. For convenience, the stored and input values are often set equal to the binary values 1 and 0. Using instead 1 and –1, as in the Hamming model, often yields improved network performance. However, because input objects do not usually contain negative values, input values of 1 and –1 ordinarily require preprocessing of the input data.
© 1990 Optical Society of America
PDF ArticleMore Like This
David Casasent
MJJ1 OSA Annual Meeting (FIO) 1990
Howard E. Motteler, L. Larrabee Strow, J. Anthony Gualtieri, Larry McMillin, and James Lo
TuD.1 Optical Remote Sensing of the Atmosphere (ORS) 1993
Shu-jen Yeh and Henry Stark
MN5 OSA Annual Meeting (FIO) 1990