Share Email Print

Proceedings Paper

Massively parallel computation of lattice associative memory classifiers on multicore processors
Author(s): Gerhard X. Ritter; Mark S. Schmalz; Eric T. Hayden
Format Member Price Non-Member Price
PDF $14.40 $18.00
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

Over the past quarter century, concepts and theory derived from neural networks (NNs) have featured prominently in the literature of pattern recognition. Implementationally, classical NNs based on the linear inner product can present performance challenges due to the use of multiplication operations. In contrast, NNs having nonlinear kernels based on Lattice Associative Memories (LAM) theory tend to concentrate primarily on addition and maximum/minimum operations. More generally, the emergence of LAM-based NNs, with their superior information storage capacity, fast convergence and training due to relatively lower computational cost, as well as noise-tolerant classification has extended the capabilities of neural networks far beyond the limited applications potential of classical NNs. This paper explores theory and algorithmic approaches for the efficient computation of LAM-based neural networks, in particular lattice neural nets and dendritic lattice associative memories. Of particular interest are massively parallel architectures such as multicore CPUs and graphics processing units (GPUs). Originally developed for video gaming applications, GPUs hold the promise of high computational throughput without compromising numerical accuracy. Unfortunately, currently-available GPU architectures tend to have idiosyncratic memory hierarchies that can produce unacceptably high data movement latencies for relatively simple operations, unless careful design of theory and algorithms is employed. Advantageously, some GPUs (e.g., the Nvidia Fermi GPU) are optimized for efficient streaming computation (e.g., concurrent multiply and add operations). As a result, the linear or nonlinear inner product structures of NNs are inherently suited to multicore GPU computational capabilities. In this paper, the authors' recent research in lattice associative memories and their implementation on multicores is overviewed, with results that show utility for a wide variety of pattern classification applications using classical NNs or lattice-based NNs. Dataflow diagrams are presented in terms of a parameterized model of data burden and LAM partitioning.

Paper Details

Date Published: 12 October 2011
PDF: 12 pages
Proc. SPIE 8136, Mathematics of Data/Image Pattern Coding, Compression, and Encryption with Applications XIII, 813604 (12 October 2011); doi: 10.1117/12.896562
Show Author Affiliations
Gerhard X. Ritter, Univ. of Florida (United States)
Mark S. Schmalz, Univ. of Florida (United States)
Eric T. Hayden, 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