Mixing floating- and fixed-point formats for neural network learning on neuroprocessors

Microprocessing and microprogramming

Volumn 41, Issue 10, 1996, Pages 757-769

  Anguita, Davide ^a   Gomes, Benedict A ^a  

^a UNIVERSITY OF GENOA   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION; COMPUTER SIMULATION; NEURAL NETWORKS; ONLINE SYSTEMS; PROGRAM PROCESSORS;

FIXED POINT FORMAT; FLOATING POINT FORMAT; MATRIX BACKPROPAGATION ALGORITHM; NEUROPROCESSORS;

LEARNING ALGORITHMS;

EID: 0030167798     PISSN: 01656074     EISSN: None     Source Type: Journal    
DOI: 10.1016/0165-6074(96)00012-9     Document Type: Article

References (28)

1. C. Alippi M.E. Negri Hardware requirements for digital VLSI implementations of neural networks Int. Joint Conf. on Neural Networks Singapore 1991 1873 1878
2. D. Anguita G. Parodi R. Zunino An efficient implementation of BP on RISC-based workstations Neurocomputing 6 1994 57 65
3. K. Asanović J. Beck B. Irissou D. Kingsbury N. Morgan J. Wawrzynek The TO vector microprocessor Hot Chips VII Symposium 13–15 Aug. 1995 Stanford Univ.,
4. K. Asanović J. Beck J. Feldman N. Morgan J. Wawrzynek Designing a connectionist network supercomputer Int. J. Neural Systems 4 4 Dec. 1993 317 326
5. K. Asanović N. Morgan Experimental determination of precision requirements for back-propagation training of artificial neural networks Proc. of 2nd Int. Conf. on Microelectronics for Neural Networks Münich, Germany 16–18 Oct. 1991 9 15
6. V. Bochev Distributed arithmetic implementation of artificial neural networks IEEE Trans. on Signal Processing 41 5 May 1993
7. H. Bourlard N. Morgan Continuous speech recognition by connectionist statistical methods IEEE Trans. on Neural Networks 4 6 Nov. 1993 893 909
8. S. Carrato A. Premoli G.L. Sicuranza Linear and nonlinear neural networks for image compression V. Cappellini A.G. Constantinides Digital Signal Processing 1991 Elsevier Amsterdam 526 531
9. G. Cybenko Approximation by superposition of a sigmoidal function Math of Control, Signal, and Systems 2 1989 303 314
10. D.D. Caviglia M. Valle G.M. Bisio Effect of weight discretization on the back propagation learning method: Algorithm design and hardware realization Proc. of IJCNN '90 San Diego, USA 17–21 June 1990 631 637
11. A. Corana C. Rolando S. Ridella A highly efficient implementation of back-propagation algorithm on SIMD computers J.-L. Delhaye E. Gelenbe High Performance Computing, Proc. of the Int. Symp. Montpellier, France 1989 Elsevier Amsterdam 181 190 (22–24 March 1989)
12. E. Fiesler, A. Choudry and H.J. Caulfield, A universal weight discretization method for multi-layer neural networks, IEEE Trans. on SMC , to appear.
13. D. Hammerstrom A VLSI architecture for high-performance, low-cost, on-chip learning Proc. of the IJCNN '90 San Diego, USA 17–21 June 1990 537 544
14. M. Hoehfeld S.E. Fahlman Learning with numerical precision using the cascade-correlation algorithm IEEE Trans. on Neural Networks 3 4 July 1992 602 611
15. P.W. Hollis J.S. Harper J.J. Paulos The effect of precision constraints in a backpropagation learning network Neural Computation 2 3 1990
16. M.A. Kramer Nonlinear principal component analysis using autoassociative neural networks AIChE J. 37 2 Feb. 1991 233 243
17. G. Kane J. Heinrich MIPS RISC Architecture 1992 Prentice Hall Englewoods Cliffs, NJ
18. N. Maudit M. Duranton J. Gobert J.A. Sirat Lneuro 1.0: a piece of hardware LEGO for building neural network systems IEEE Trans. on Neural Networks 3 3 May 1992 414 421
19. N. Morgan H. Bourlard Factoring networks by a statistical method Neural Computation 4 6 Nov. 1992 835 838
20. U. Ramacher VLSI Design of Neural Networks 1991 Kluwer Academic Dordrecht
21. U. Ramacher SYNAPSE-X: a general-purpose neurocomputer Proc. of the 2nd Int. Conf. on Microelectronics for Neural Networks Münich, Germany Oct. 1991 401 409
22. S. Sakaue T. Kohda H. Yamamoto S. Maruno Y. Shimeki Reduction of required precision bits for back-propagation applied to pattern recognition IEEE Trans. on Neural Networks 4 2 March 1993 270 275
23. J.A. Sirat S. Makram-Ebeid J.L. Zorer J.P. Nadal Unlimited accuracy in layered networks IEEE Int. Conf. on Artificial Neural Networks London 1989 181 185
24. T.J. Sejnowsky C.R. Rosenberg Parallel networks that learn to pronounce English text Complex Systems 1 1987 145 168
25. G. Tesauro T.J. Sejnowsky A neural network that learns to play backgammon D.Z. Anderson Neural Information Processing Systems 1987 442 456
26. T. Tollenaere SuperSAB: fast adaptive back propagation with good scaling properties Neural Networks 3 5 1990 561 573
27. T.P. Vogl J.K. Mangis A.K. Rigler W.T. Zink D.L. Alkon Accelerating the covergence of the back-propagation method Biological Cybernetics 59 1989 257 263
28. J. Wawrzynek K. Asanović N. Morgan The design of a neuro-microprocessor IEEE Trans. on Neural Networks 4 3 May 1993 394 399