Novel architecture and synapse design for hardware implementations of neural networks

Computers and Electrical Engineering

Volumn 24, Issue 1-2, 1998, Pages 75-87

  McGinnity, T M ^a   Roche, B ^a   Maguire, L P ^a   McDaid, L J ^a  

^a UNIVERSITY OF ULSTER   (United Kingdom)

Author keywords

Hardware implementation; Neural network; VLSI

Indexed keywords

EID: 0346906920     PISSN: 00457906     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0045-7906(97)00043-8     Document Type: Article

References (21)

1. Hammerstrom D. Electronic neural network implementation, Tutorial No. 5., International Joint Conference on Neural Networks, Baltimore, MD, 1992.
2. Boser B E, Sackeninger E, Bromeley J, LeCun Y, Jackal L D. Hardware requirements for neural network pattern classifiers. IEEE Micro. 1992;12:32-40.
3. Stout M G, Salmon, L G, Rudolph, G L Martinez, T. R. A multi-chip module implementation of a neural network. In Proc. 1994 IEEE Multi-Chip Module Conference. Santa Cruz, CA, 1994, pp. 15-17 March.
4. Craven M P, Curtis K M, Hayes-Gill B R. Consideration of multiplexing in neural network hardware. IEEE Proc. Circuits, Devices and Systems 1994;141(3):237-40.
5. Nosratinia A, Ahmadi M Sridhar M, Performance analysis and improvements on a hybrid cascade architecture for multi-layer neural networks. In Proc. of the 35th Midwest Symposium on Circuits and Systems. Vol. 2, 9-12 August 1992, pp. 1214-1217.
6. Elias J G, Chu H-H Meshrekim S M, Silicon implementation of an artificial dendritic tree. In IJCNN International Joint Conference on Neural Networks, Vol. 1. Baltimore, MD 1992, 7-11 June, pp. 154-159.
7. Curtis K M, Rouse M M Hayes-Gill B R, A novel neural network architecture for text to speech conversion. In Proc. of the IASTED International Symposium Artificial Intelligence Application and Neural Networks-AINN '90. Zurich, Switzerland, 25-27 June 1990, pp. 164-167.
8. Nakamoto T, Takagi H, Moriizumi T. An analog back propagation circuit. Trans. Inst. Electronics, Information and Communication Engineers D-11 1992; J75D-II IEE:1:128-36.
9. Nakamoto T, Takagi H, Moriizumi T. An analog back propagation circuit. Trans. Inst. Electronics, Information and Communication Engineers D-11 1992; J75D-II IEE:1:128-36.
10. Marchesi M, Orlandi G, Piazza F, Uncini A. Fast neural networks without multipliers. IEEE Trans. Neural Networks 1993;4(1):53-62.
11. Campbell C. Learning beyond saturation, Fifth Irish Neural Networks Conference, Maynooth, 6-14 1995.
12. Mezard M, Nadal J P. Learning in feedforward layer networks, the Tiling algorithm. J. Phys. 1989;A22:2191-203.
13. McGinnity T M, McDaid L J, Campbell J G. Modeling optimum architectures for VLSI implementations of artificial neural networks, Fifth Irish Neural Networks Conference, Maynooth, 143-151 1995.
14. Masaki A, Hirai Y, Yamada M. Neural networks in CMOS: a case study. IEEE Circuits and Devices Mag. 1990;6(Pt. 2):12-17.
15. Mead C A, Conway L, Introduction to VLSI Systems, 2nd Ed. Addison Wesley, 1980.
16. Roche B, McGinnity T M, McDaid L, Hashim A A, Novel synapse design for VLSI implementation of neural networks. In Proc. 4th Int. Conf. on Soft Computing IIZUKA'96. Japan, Vol. 2, 1996, pp. 718-721.
17. Haykin S. Neural Networks: A Comprehensive Foundation. Macmillan, New York, 1994.
18. Cybenko G. Approximation by superposition of a sigmoidal function. Math. Control, Signals System 1989;2:303-14.
19. Hinton G E. How neural networks learn from experience. Sci. Amer. 1992;September:105-26.
20. Cover T. Geometrical and structural properties of systems of linear equations with applications in pattern recognition. IEEE Trans. Electron. Computing 1965;14:326-34.
21. Gardner E. The space of interactions in neural networks. J. Phys. 1988;A21:257-70.