Recurrent neural networks with backtrack-points and negative reinforcement applied to cost-based abduction
DOI10.1016/J.NEUNET.2005.06.026zbMath1077.68747DBLPjournals/nn/AbdelbarEAW05OpenAlexW2070278423WikidataQ46947215 ScholiaQ46947215MaRDI QIDQ2568027
Donald C. II Wunsch, Ashraf M. Abdelbar, Emad A. M. Andrews, Mostafa A. El-Hemaly
Publication date: 7 October 2005
Published in: Neural Networks (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.neunet.2005.06.026
Bayesian networksbelief revisionreasoning under uncertaintyrecurrent networkscost-based abductionhigh-order networks
Learning and adaptive systems in artificial intelligence (68T05) Reasoning under uncertainty in the context of artificial intelligence (68T37)
Related Items (1)
Cites Work
- Unnamed Item
- Approximating cost-based abduction is NP-hard
- A linear constraint satisfaction approach to cost-based abduction
- Cost-based abduction and MAP explanation
- Networked bubble propagation: a polynomial-time hypothetical reasoning method for computing near-optimal solutions
- Reasoning, nonmonotonicity and learning in connectionist networks that capture propositional knowledge
- Recurrent neural networks with backtrack-points and negative reinforcement applied to cost-based abduction
- Polynomial solvability of cost-based abduction
- Neural networks and physical systems with emergent collective computational abilities.
- An efficient LP-based admissible heuristic for cost-based abduction
- An algorithm for finding MAPs for belief networks through cost-based abduction
This page was built for publication: Recurrent neural networks with backtrack-points and negative reinforcement applied to cost-based abduction
