TY - JOUR
T1 - Neural network solutions to logic programs with geometric constraints
AU - Parikh, Jo Ann
AU - Werkheiser, Anne
AU - Subrahmanian, V. S.
N1 - Funding Information:
This work was supported by the U.S. Army Topographic Engineering Center under the auspices of the U. S. Army Research Office Scientific Services Program administered by Battelle (Delivery Orders 436 and 532, Contract No. DAAL03-91-C-0034). Subrahmanian was supported by the Army Research Office under grant number DAAL03-92-G-0225 and Parikh was supported in part by National Science Foundation grant IRI-9108638. It is a pleasure to acknowledge Barbara Jayne and Vanessa Zalegowski for illustrations and slides, and Cathy Wiley, research librarian at the Navy Center for Applied Research in Artificial Intelligence, for help with references and reprints. This paper could not easily have been completed without them.
Funding Information:
This work was supported by the U. S. Army Topographic Engineering Center under the auspices of the U. S. Army Research Office Scientific Services Program administered by Battelle (Delivery Orders 436 and 532, Contract No. DAALO3-91-C-0034). Subrahmanian was supported by the Army Research Office under grant number DAALO3-92-G-0225 and Parikh was supported in part by National Science Foundation grant IRI-9108638. It is a pleasure to acknowledge Barbara Jayne and Vanessa Zalegowski for illustrations and slides, and Cathy Wiley, research librarian at the Navy Center for Applied Research in Artificial Intelligence, for help with references and reprints. This paper could not easily have been completed without them.
Publisher Copyright:
© 1993 SPIE. All rights reserved.
PY - 1993/9/2
Y1 - 1993/9/2
N2 - Hybrid knowledge bases (HKBs), proposed by Nerode and Subrahmanian, provide a uniform theoretical framework for dealing with the mixed data types and multiple reasoning modes required for solving logical deployment problems. Algorithms based on mixed integer linear programming techniques have been developed for the syntactic subset of HKBs corresponding to function-free Prolog-like logic programs. In this study, we examine the ability of neural networks to solve a more comprehensive set of problems expressed within the hybrid knowledge base framework. The objective of this research is to design and implement a nonlinear optimization procedure for solving extended logic programs with neural networks. We focus upon two types of extensions which are typically required in the formulation of logical deployment problems. The first type of extension, which we shall refer to as a Type I extension, consists of embedding numerical and geometric constraints into logic programs. The second type of extension, which we shall call a Type II extension, consists of incorporating optimization problems into logic clauses.
AB - Hybrid knowledge bases (HKBs), proposed by Nerode and Subrahmanian, provide a uniform theoretical framework for dealing with the mixed data types and multiple reasoning modes required for solving logical deployment problems. Algorithms based on mixed integer linear programming techniques have been developed for the syntactic subset of HKBs corresponding to function-free Prolog-like logic programs. In this study, we examine the ability of neural networks to solve a more comprehensive set of problems expressed within the hybrid knowledge base framework. The objective of this research is to design and implement a nonlinear optimization procedure for solving extended logic programs with neural networks. We focus upon two types of extensions which are typically required in the formulation of logical deployment problems. The first type of extension, which we shall refer to as a Type I extension, consists of embedding numerical and geometric constraints into logic programs. The second type of extension, which we shall call a Type II extension, consists of incorporating optimization problems into logic clauses.
UR - http://www.scopus.com/inward/record.url?scp=85075824346&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075824346&partnerID=8YFLogxK
U2 - 10.1117/12.152530
DO - 10.1117/12.152530
M3 - Conference article
AN - SCOPUS:85075824346
SN - 0277-786X
VL - 1965
SP - 298
EP - 311
JO - Proceedings of SPIE - The International Society for Optical Engineering
JF - Proceedings of SPIE - The International Society for Optical Engineering
T2 - Applications of Artificial Neural Networks IV 1993
Y2 - 11 April 1993 through 16 April 1993
ER -