Share Email Print

Proceedings Paper

Failure of outer-product learning to perform higher-order mapping
Author(s): Jason M. Kinser
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Outer-product learning (also referred to as Hebbian learning) has been used as a very simple training algorithm for neural networks. Outer-product learning also has been proposed as a method for training a network with higher-order interconnections. It is shown in this paper that outer-product learning is inappropriate for higher-order networks because it does not have the ability to perform a non-monotonic mapping.

Paper Details

Date Published: 1 November 1991
PDF: 12 pages
Proc. SPIE 1541, Infrared Sensors: Detectors, Electronics, and Signal Processing, (1 November 1991); doi: 10.1117/12.49333
Show Author Affiliations
Jason M. Kinser, Teledyne Brown Engineering (United States)

Published in SPIE Proceedings Vol. 1541:
Infrared Sensors: Detectors, Electronics, and Signal Processing
T. S. Jay Jayadev, Editor(s)

© SPIE. Terms of Use
Back to Top