Share Email Print
cover

Proceedings Paper

Noise tolerant dendritic lattice associative memories
Author(s): Gerhard X. Ritter; Mark S. Schmalz; Eric Hayden; Marc Tucker
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Linear classifiers based on computation over the real numbers R (e.g., with operations of addition and multiplication) denoted by (R, +, x), have been represented extensively in the literature of pattern recognition. However, a different approach to pattern classification involves the use of addition, maximum, and minimum operations over the reals in the algebra (R, +, maximum, minimum) These pattern classifiers, based on lattice algebra, have been shown to exhibit superior information storage capacity, fast training and short convergence times, high pattern classification accuracy, and low computational cost. Such attributes are not always found, for example, in classical neural nets based on the linear inner product. In a special type of lattice associative memory (LAM), called a dendritic LAM or DLAM, it is possible to achieve noise-tolerant pattern classification by varying the design of noise or error acceptance bounds. This paper presents theory and algorithmic approaches for the computation of noise-tolerant lattice associative memories (LAMs) under a variety of input constraints. Of particular interest are the classification of nonergodic data in noise regimes with time-varying statistics. DLAMs, which are a specialization of LAMs derived from concepts of biological neural networks, have successfully been applied to pattern classification from hyperspectral remote sensing data, as well as spatial object recognition from digital imagery. The authors' recent research in the development of DLAMs is overviewed, with experimental results that show utility for a wide variety of pattern classification applications. Performance results are presented in terms of measured computational cost, noise tolerance, classification accuracy, and throughput for a variety of input data and noise levels.

Paper Details

Date Published: 7 October 2011
PDF: 14 pages
Proc. SPIE 8136, Mathematics of Data/Image Pattern Coding, Compression, and Encryption with Applications XIII, 813602 (7 October 2011); doi: 10.1117/12.896560
Show Author Affiliations
Gerhard X. Ritter, Univ. of Florida (United States)
Mark S. Schmalz, Univ. of Florida (United States)
Eric Hayden, Univ. of Florida (United States)
Marc Tucker, Univ. of Florida (United States)


Published in SPIE Proceedings Vol. 8136:
Mathematics of Data/Image Pattern Coding, Compression, and Encryption with Applications XIII
Mark S. Schmalz; Gerhard X. Ritter; Junior Barrera; Jaakko T. Astola, Editor(s)

© SPIE. Terms of Use
Back to Top