Display options
Cite
Kusnadi K, Beebe C, Carothers JD. Digraph visualization using a neural algorithm with a heuristic activation scheme. IEEE Trans Syst Man Cybern B Cybern. 1998;28(4):562-72doi: 10.1109/3477.704295.
Kusnadi, K., Beebe, C., & Carothers, J. D. (1998). Digraph visualization using a neural algorithm with a heuristic activation scheme. IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society, 28(4), 562-72. https://doi.org/10.1109/3477.704295
Kusnadi, K, et al. "Digraph visualization using a neural algorithm with a heuristic activation scheme." IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society vol. 28,4 (1998): 562-72. doi: https://doi.org/10.1109/3477.704295
Kusnadi K, Beebe C, Carothers JD. Digraph visualization using a neural algorithm with a heuristic activation scheme. IEEE Trans Syst Man Cybern B Cybern. 1998;28(4):562-72. doi: 10.1109/3477.704295. PMID: 18255975.
Copy Download .nbib Format: NLM
Share it on

IEEE Trans Syst Man Cybern B Cybern. 1998;28(4):562-72. doi: 10.1109/3477.704295.

Digraph visualization using a neural algorithm with a heuristic activation scheme.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society

K Kusnadi, C Beebe, J D Carothers

Affiliations

  1. Dept. of Electr. & Comput. Eng., Arizona Univ., Tucson, AZ.

PMID: 18255975 DOI: 10.1109/3477.704295

Abstract

This paper presents an activation scheme for use with Hopfield neural network algorithms that guarantees a valid solution for a particular category of problems. The technique monitors the appropriate neurons and heuristically controls their activation function. As a result it has been possible to eliminate several constraint terms from the energy function that normally would have been required to drive the network toward a valid solution. This saves time and eliminates the need for empirically determining a larger number of constants. This technique has been applied to the combinatorial optimization problem called hierarchical digraph visualization that arises in many application areas where it is necessary to visually realize the relationship between entities in complex systems. Results are presented that compare this new approach with a more traditional neural network approach as well as heuristic approaches, performance improvement in terms of the solution quality as well as execution time relative to both alternative techniques was achieved.

Publication Types