Negative reinforcement and backtrack-points for recurrent neural networks for cost-based abduction

A.M. Abdelbar, M.A. El-Hemaly, E.A.M. Andrews, D.C. Wunsch
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.  
Abduction is the process of proceeding from data II. PENAL describing a set of observations or events, to a set of hypothe-. ses which best explains or accounts for the data. Cost-based A High Order abduction (CBA) is an Al formalism in which evidence to be A recurrent nf explained is treated as a goal to be proven, proofs have costs ogy of inter-neui based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost In the case of
doi:10.1109/ijcnn.2005.1555959 fatcat:qxysc43zn5duxk4r2a7dk5m3m4