Scholars' Mine
Missouri S&T
Research Repository
Curtis Laws Wilson Library
400 W. 14th Street
Rolla, MO 65409-0060
scholarsmine@mst.edu
| Title: | Negative reinforcement and backtrack-points for recurrent neural networks for cost-based abduction | |
| Author (s): | Abdelbar, A.M. El-Hemaly, M.A. Andrews, E.A.M. Wunsch, Donald C. | |
| Department/Lab Affiliations: | Applied Computational Intelligence Laboratory Electrical and Computer Engineering | |
| Keywords: | backtrack-points cost-based abduction heuristic perturbations high order recurrent neural networks learning (artificial intelligence) negative reinforcement perturbation techniques recurrent neural nets | |
| Issue Date: | 2005 | |
| Publisher: | Institute of Electrical and Electronics Engineers | |
| Citation: | Abdelbar, A.M.; El-Hemaly, M.A.; Andrews, E.A.M.; Wunsch, D.C., II, "Negative reinforcement and backtrack-points for recurrent neural networks for cost-based abduction" IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on Neural Networks, pp. 827- 832 vol. 2, 31 July-4 Aug. 2005 | |
| Abstract: | Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CKA) is an AI formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In this paper, we introduce two techniques for improving the performance of high order recurrent networks (HORN) applied to cost-based abduction. In the backtrack-points technique, we use heuristics to recognize early that the network trajectory is moving in the wrong direction; we then restore the network state to a previously-stored point, and apply heuristic perturbations to nudge the network trajectory in a different direction. In the negative reinforcement technique, we add hyperedges to the network to reduce the attractiveness of local-minima. We apply these techniques on a 300-hypothesis, 900-rule particularly-difficult instance of CBA. | |
| Type: | Article - Conference proceedings text | |
| Copyright Notice: | This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. FULL COPYRIGHT INFORMATION: | |
| Publisher URL: | ||
| Link to this page: | ||
| Full Text: |
|
| title | Negative reinforcement and backtrack-points for recurrent neural networks for cost-based abduction | |
| contributor.author | Abdelbar, A.M. | |
| contributor.author | El-Hemaly, M.A. | |
| contributor.author | Andrews, E.A.M. | |
| contributor.author | Wunsch, Donald C. | |
| contributor.deptlab | Applied Computational Intelligence Laboratory | |
| contributor.deptlab | Electrical and Computer Engineering | |
| subject | backtrack-points | |
| subject | cost-based abduction | |
| subject | heuristic perturbations | |
| subject | high order recurrent neural networks | |
| subject | learning (artificial intelligence) | |
| subject | negative reinforcement | |
| subject | perturbation techniques | |
| subject | recurrent neural nets | |
| date.issued | 2005 | |
| date.submitted | 2007 | |
| publisher | Institute of Electrical and Electronics Engineers | |
| identifier.citation | Abdelbar, A.M.; El-Hemaly, M.A.; Andrews, E.A.M.; Wunsch, D.C., II, "Negative reinforcement and backtrack-points for recurrent neural networks for cost-based abduction" IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on Neural Networks, pp. 827- 832 vol. 2, 31 July-4 Aug. 2005 | |
| identifier.pub.URI | ||
| description.abstract | Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CKA) is an AI formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In this paper, we introduce two techniques for improving the performance of high order recurrent networks (HORN) applied to cost-based abduction. In the backtrack-points technique, we use heuristics to recognize early that the network trajectory is moving in the wrong direction; we then restore the network state to a previously-stored point, and apply heuristic perturbations to nudge the network trajectory in a different direction. In the negative reinforcement technique, we add hyperedges to the network to reduce the attractiveness of local-minima. We apply these techniques on a 300-hypothesis, 900-rule particularly-difficult instance of CBA. | |
| type | Article - Conference proceedings | |
| type.DCMIType | text | |
| type.status | Final version | |
| rights | This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. | |
| rights.URI | ||
| date.accessioned | 2007-04-05T14:25:17Z | |
| date.available | 2007-04-05T14:25:16Z | |
| identifier.persist.URI | ||
| Full Text |
|