Title :
Distributed computation for neural-based abductive reasoning
Author :
Romdhane, L.B. ; Elhadef, M.
Author_Institution :
Dept. of Comput. Sci., Faculty of Sci. of Monastir, Tunisia
fDate :
31 July-4 Aug. 2005
Abstract :
This work extends a recent model for neural-based abductive reasoning to account for the monotonic class. A problem is said to be monotonic some causes, together, explain the same effect. For this, we developed a new computational principle, called the softmin, and implemented it within a neural architecture. Simulation results are very satisfactory and should stimulate future research.
Keywords :
inference mechanisms; neural nets; distributed computation; monotonic class; neural architecture; neural-based abductive reasoning; Artificial neural networks; Coherence; Computational modeling; Computer architecture; Distributed computing; Hopfield neural networks; Packet radio networks; Proposals; Speech recognition; Traveling salesman problems;
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Print_ISBN :
0-7803-9048-2
DOI :
10.1109/IJCNN.2005.1555960
