A case study of a distributed high-performance computing system for neurocomputing

Journal of Systems Architecture

Volumn 46, Issue 5, 2000, Pages 429-438

  Anguita, D ^a   Boni, A ^a   Parodi, G ^a  

^a UNIVERSITY OF GENOA   (Italy)

Author keywords

Neurocomputing; Statistical validation; Workstation cluster

Indexed keywords

COMPUTER ARCHITECTURE; COMPUTER WORKSTATIONS; FEEDFORWARD NEURAL NETWORKS; STATISTICAL METHODS;

NEUROCOMPUTING;

DISTRIBUTED COMPUTER SYSTEMS;

EID: 0034159583     PISSN: 13837621     EISSN: None     Source Type: Journal    
DOI: 10.1016/S1383-7621(99)00017-X     Document Type: Article

References (18)

1. Anderson E.C., Dongarra J. Performance of LAPACK: A portable library of numerical linear algebra routines. Proc. IEEE. 81:1993;1094-1101.
2. Anguita D., Parodi G., Zunino R An efficient implementation of BP on RISC based workstations. Neurocomputing. 6:1994;57-65.
3. Anguita D., Gomes B.A. Mixing floating- and fixed-point formats for neural network learning on neuroprocessors. Microprocessing and Microprogramming. 41:1996;757-769.
4. C. Bishop, Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995.
5. A. Corana, C. Rolando, S. Ridella, A highly efficient implementation of back-propagation algorithm on SIMD computers, in: J.-L. Delhaye, E. Gelenbe (Eds.), High Performance Computing (1989) 181-190.
6. Corana A., Rolando C., Ridella S. Use of Level 3 BLAS Kernels in neural networks: The back-propagation algorithm. Parallel Computing. 89:1990;269-274.
7. A. Geist et al., PVM: Parallel Virtual Machine, a User's Guide and Tutorial for Networked Parallel Computing, The MIT Press, 1994.
8. J.S. Hjorth, Computer Intensive Statistical Methods: Validation Model Selection and Bootstrap, Chapman & Hall, London, 1994.
9. R. Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection, in: Proc. IJCAI 1995, Montreal, Canada, 1995.
10. B. LeBaron, A.S. Weigend, Bootstrap evaluation of the effect of data splitting on financial time series. IEEE Transaction on Neural Network 9(1) (1998) 213-220.
11. F. Leisch, L.C. Jain, K. Hornik, Cross-validation with active pattern selection for neural network classifiers. IEEE Transaction on Neural Network 9(1) (1998) 35-41.
12. P.M. Murphy, D.W. Aha, UCI Repository of machine learning databases, http://www.ics.uci.edu/ mlearn/MLRepository.html, University of California, Department of Information and Computer Science, Irvine, CA, 1994.
13. S.J. Raudys, A.K. Jain, Small sample size effects in statistical pattern recognition: recommendations for practioners, IEEE Transaction on Pattern Analysis and Machine Intelligence 13 (1991) 252-263.
14. S. Rovetta, R. Zunino, L. Buffrini, G. Rovetta, Prototyping neural networks learn Lyme borreliosis, in: Proceedings of the 8th IEEE Symposium on Computer Based Medical Systems, Lubbock, Texas, USA, 9-11 June 1995.
15. D.W. Ruck, S.K. Rogers, M. Kabrisky, M.E. Oxley, B.W. Suter, The multilayer perceptron as an approximation to a bayes optimal discriminant function, IEEE Transactions on Neural Networks 1 (1990).
16. V.N. Vapnik, The Nature of Statistical Learning Theory, Springer, Berlin, 1995.
17. T. Plate, P. Band, J. Bert, J. Grace, A comparison between neural networks and other statistical techniques for modelling the relationship between tobacco and alcohol and cancer, in: M.C. Mozer, M.I. Jordan, T. Petsche (Eds.), Advances in Neural Information Processing Systems, vol. 9, The MIT Press, Cambridge, 1997, pp. 967-973.
18. C. Wang, S.S. Venkatesh, J.S. Judd, Optimal stopping and effective machine complexity in learning, in: J.D. Cowan, G. Tesauro, J. Alspector (Eds.), Advances in Neural Information Processing Systems, Morgan-Kaufmann, vol. 6, 1994, pp. 303-310.