Abstract
Higher-order neural networks1have several desirable computational characteristics such as significantly decreased convergence times, increased storage capacity over first-order layered networks (which respond only to weighted sums of the inputs ), and an ability to encode a prioriknowledge in the network. Simulation results for the problem of learning to classify clusters in a binary string showed that a second-order network (which also includes weighted sums of products ) generalized correctly 90% of the time after training on only 10% of the training set.
© 1987 Optical Society of America
PDF ArticleMore Like This
Alexandre Jouan and Henri H. Arsenault
MA1 OSA Annual Meeting (FIO) 1987
Claude Lejeune, Young Sheng, and Henri H. Arsenault
MII2 OSA Annual Meeting (FIO) 1991
Yanxin X. Zhang and Guogang G. Mu
MBB3 OSA Annual Meeting (FIO) 1992