Share Email Print
cover

Proceedings Paper • new

Joint proximity association template for neural networks (Conference Presentation)
Author(s): James LaRue
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

A technical solution is described for implementing a computer-executed system of association memory matrices to replace the proximal layers of a convolutional neural network (CNN). An example method includes configuring one Associative Memory Matrix (AMM) for each configured layer in the CNN. This one-to-one conversion method motivates the name to the product: the Joint Proximity Association Template (JPAT) for Neural Networks. The invention is a numerically stable soft-ware based implementation that (1) reduces the long training times, (2) reduces the execution time, and (3) produces bidirectional intra-layer connections and potentially, inter-layer connections as well. The method further includes, potentially, forming a single AMM, from the multiple AMMs corresponding to the multiple and proximal layers of the CNN, in anticipation of the well-known Universal Approximation Theorem.

Paper Details

Date Published: 14 May 2018
PDF
Proc. SPIE 10652, Disruptive Technologies in Information Sciences, 1065214 (14 May 2018); doi: 10.1117/12.2326891
Show Author Affiliations
James LaRue, dba Jadco Signals (United States)


Published in SPIE Proceedings Vol. 10652:
Disruptive Technologies in Information Sciences
Misty Blowers; Russell D. Hall; Venkateswara R. Dasari, Editor(s)

© SPIE. Terms of Use
Back to Top