Abstract. Experiments of neural network training procedure parallelization are conducted. Several styles of parallelization are described and compared, estimations of neural networ...
We present an approach to keyhole plan recognition which uses a dynamic belief (Bayesian) network to represent features of the domain that are needed to identify users’ plans and...
David W. Albrecht, Ingrid Zukerman, Ann E. Nichols...
Idle workstations in a network represent a significant computing potential. In particular, their processing power can be used by parallel-distributed programs that treat the netwo...
Michael J. Feeley, Brian N. Bershad, Jeffrey S. Ch...
This paper presents an architecture for web-based interaction and steering of parallel/distributed scientific applications. The architecture is composed of detachable thin-clients ...