Implementing Invariances In High Order Neural Nets

T. Maxwell; C. L. Giles; Y. C. Lee; H. H. Chen

doi:10.1117/12.939983

21 August 1987 Implementing Invariances In High Order Neural Nets

T. Maxwell, C. L. Giles, Y. C. Lee, H. H. Chen

Proceedings Volume 0754, Optical and Digital Pattern Recognition; (1987) https://doi.org/10.1117/12.939983
Event: OE LASE'87 and EO Imaging Symposium, 1987, Los Angeles, CA, United States

Abstract

In this paper we examine the properties of high order neuron-like adaptive learning units whose output is invariant under an arbitrary finite group of transformations on the input space. The transformation invariance is imposed by averaging the input of each unit over a transformation group, thus eliminating the capacity of the units to detect features which are incompatible with the imposed group invariance. This averaging process also generates equivalence classes of interactions among the units, and thus allows a collapse of the interaction weight matrix, reducing the number of high order terms. As an example, we discuss the implementation of two types of translation invariance.

Citation Download Citation

T. Maxwell, C. L. Giles, Y. C. Lee, and H. H. Chen "Implementing Invariances In High Order Neural Nets", Proc. SPIE 0754, Optical and Digital Pattern Recognition, (21 August 1987); https://doi.org/10.1117/12.939983

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available