relaxation rate, constraint satisfaction networks
Constraint satisfaction networks contain nodes that receive weighted evidence from external sources and/or other nodes. A relaxation process allows the activation of nodes to affect neighboring nodes, which in turn can affect their neighbors, allowing information to travel through a network. When doing discrete updates (as in a software implementation of a relaxation network), a goal net or goal activation can be computed in response to the net input into a node, and a relaxation rate can then be used to determine how fast the node moves from its current value to its goal value. An open question was whether or not the relaxation rate is a sensitive parameter. This paper shows that the relaxation rate has almost no effect on how information flows through the network as long as it is small enough to avoid large discrete steps and/or oscillation.
Original Publication Citation
Wilson, D. R., Ventura D., Moncur B., and Martinez, T. R., "The Robustness of Relaxation Rates in Constraint Satisfaction Networks", Proceedings of the IEEE International Joint Conference on Neural Networks IJCNN'99, CD paper #162, 1999.
BYU ScholarsArchive Citation
Martinez, Tony R.; Ventura, Dan A.; Wilson, D. Randall; and Moncur, Brian, "The Robustness of Relaxation Rates in Constraint Satisfaction Networks" (1999). All Faculty Publications. 1124.
Physical and Mathematical Sciences
© 1999 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Copyright Use Information