论文信息 - Training of Neural Networks: Interactive Possibilities in a Distributed Framework

Training of Neural Networks: Interactive Possibilities in a Distributed Framework

Training of Artificial Neural Networks in a Distributed Environment is considered and applied to a typical example in High Energy Physics interactive analysis. Promising results showing a reduction of the wait time from 5 hours to 5 minutes obtained in a local cluster with 64 nodes are described. Preliminary tests in a wide area network studying the impact of latency time are described; and the future work for integration in a GRID framework, that will be carried in the CrossGrid European Project, is outlined.

[1] Teuvo Kohonen,et al. Self-Organizing Maps , 2010 .

[2] Torbjörn Sjöstrand,et al. The Lund Monte Carlo for jet fragmentation and e+e- physics - jetset version 6.2 , 1986 .

[3] Ian Foster,et al. The Grid 2 - Blueprint for a New Computing Infrastructure, Second Edition , 1998, The Grid 2, 2nd Edition.

[4] Douglas Aberdeen,et al. 92¢ /MFlops/s, Ultra-Large-Scale Neural-Network Training on a PIII Cluster , 2000, ACM/IEEE SC 2000 Conference (SC'00).

[5] et al,et al. Search for the Standard Model Higgs boson at LEP in the year 2000 , 2001, hep-ex/0102036.