Edward Michael Williams

Learn More
Belief updating in Bayes nets, a well known computationally hard problem, has recently been approximated by several deterministic algorithms, and by various randomized approximation algorithms. Deterministic algorithms usually provide probability bounds, but have an exponential runtime. Some randomized schemes have a polynomial runtime, but provide only(More)
Belief updating in Bayes nets, a well known computationally hard problem, has recently been approximated by several deterministic algorithms, and by various randomized ap­ proximation algorithms. Deterministic algo­ rithms usually provide probability bounds, but have an exponential runtime. Some ran­ domized schemes haw! a polynomial runtime, but provide(More)
Approved for public release; distribution unlimited The views expressed in this dissertation are those of the author and do not reeect the oocial policy or position of the Department of Defense or the United States Government. Acknowledgements I would like to thank my advisor, Dr. Eugene Santos, for his insight and guidance throughout this eeort. I am also(More)
Numerous artiicial intelligence schemes and applications require, at their core, a solution to intractable computational problems, such as probabilistic reasoning. Conditions for theorems guaranteeing polynomial time algorithms for special cases, do not hold for many real-world problem instances. While there are a number of highly specialized(More)
We develop a new method for handling incomplete knowledge when inferencing over Bayesian Knowledge Bases(BKB) using genetic algorithms(GA). The tness function for a genetic algorithm requires that we give a score to each solution it generates. When a solution is complete, we can use the joint probability of our generated solution, but when incompleteness(More)
Anytime algorithms have demonstrated their usefulness in solving many classes of intractable and NP-hard problems. This approach allows the potential for improvement in the quality of the solution to be balanced against the cost of generating that improvement , both in time and system resources. While significant work has been accomplished on characterizing(More)
Belief updating in Bayes nets, a well known computationally hard problem, has recently been approximated by several deterministic algorithms, and by various randomized approximation algorithlns. Deterministic algorithms usually provide probability bounds, but have an exponential runtime. Some ran-domized schemes haw ~, a polynomial runtime, but provide only(More)
  • 1