Share Email Print

Proceedings Paper

Training minimal artificial neural network architectures for subsoil object detection
Author(s): Kenneth D. Boese; Donald E. Franklin; Andrew B. Kahng
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We cast the training of minimal artificial neural network architectures as a problem of global optimization, and study the simulated annealing (SA) global optimization heuristic under a 'best-so-far' model. Our testbed consists of separated-aperature radar data for subsoil mine detection. In previous analyses, we have found that the traditional SA 'cooling' paradigm can be suboptimal for small instances of combinatorial global optimizations. Here, we demonstrate that traditional cooling is also suboptimal for training minimal neural networks for mine detection. Related issues include (i) how to find minimal network architectures; (ii) considering tradeoffs between minimality and trainability; (iii) the question of whether multistart/parallel implementations of SA can be superior to a single long SA run; and (iv) adaptive annealing strategies based on the best-so-far objective.

Paper Details

Date Published: 20 June 1995
PDF: 12 pages
Proc. SPIE 2496, Detection Technologies for Mines and Minelike Targets, (20 June 1995); doi: 10.1117/12.211384
Show Author Affiliations
Kenneth D. Boese, Univ. of California/Los Angeles (United States)
Donald E. Franklin, U.S. Army Night Vision & Electronic Sensors Directorate (United States)
Andrew B. Kahng, Univ. of California/Los Angeles (United States)

Published in SPIE Proceedings Vol. 2496:
Detection Technologies for Mines and Minelike Targets
Abinash C. Dubey; Ivan Cindrich; James M. Ralston; Kelly A. Rigano, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?