A modified ART 1 algorithm more suitable for VLSI implementations

Neural Networks

Volumn 9, Issue 6, 1996, Pages 1025-1043

  Serrano Gotarredona, Teresa ^a   Linares Barranco, Bernabé ^a,b  

^a INSTITUTO DE MICROELECTRÓNICA DE SEVILLA   (Spain)

^b Centro Informatico Cientifico de Andalucia   (Spain)

Author keywords

adaptive resonance theory (ART); mathematical and computational analysis; VLSI friendly algorithms

Indexed keywords

COMPUTATIONAL COMPLEXITY; COMPUTER ARCHITECTURE; NEURAL NETWORKS; NUMERICAL ANALYSIS; PATTERN RECOGNITION; VLSI CIRCUITS;

ADAPTIVE RESONANCE THEORY (ART);

LEARNING ALGORITHMS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; LEARNING; MATHEMATICAL ANALYSIS; PATTERN RECOGNITION; PRIORITY JOURNAL;

EID: 0030221432     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(95)00145-X     Document Type: Article

References (17)

1. Bult K., Wallinga A class of analog CMOS circuits based on the square law characteristics of an MOS transistor in saturation. IEEE Journal of Solid-State Circuits. SC-22(3):1987;357-365.
2. Carpenter G.A., Gjaja M.N. Fuzzy ART choice functions. Proceedings of the 1994 World Congress on Neural Networks (WCNN'94). I:1994;713-722.
3. Carpenter G.A., Grossberg S A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision, Graphics, and Image Processing. 37:1987;54-115.
4. Carpenter G.A., Grossberg S ART 2: self-organization of stable category recognition codes for analog input patterns. Applied Optics. 26(23):1987;4919-4930. 1 December.
5. Carpenter G.A., Grossberg S. ART 3: hierarchical search using chemical transmitters in self-organizing pattern recognition architectures. Neural Networks. 3:1990;129-152.
6. Carpenter G.A., Grossberg S., Markuzon N., Reynolds J.H., Rosen D.B. Fuzzy ARTMAP: a neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Transactions on Neural Networks. 3(5):1992;698-712. September.
7. Carpenter G.A., Grossberg S., Reynolds J.H. ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network. Neural Networks. 4:1991;565-588.
8. Carpenter G.A., Grossberg S., Rosen D.B. Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks. 4:1991;759-771.
9. Cavanagh, J.J F. (1995). Digital computer arithmetic. New York: McGraw-Hill.
10. Gilbert, B. (1990). Current-mode circuits from a translinear viewpoint: A tutorial. In C. Toumazou, F.J. Lidghey, & D.G. Haigh (Eds.), Analogue IC design: the current-mode approach. IEE Circuits and Systems Series 2. London: Peter Peregrinus Ltd (Chapter 2, pp. 11-91).
11. Ho C.S., Liou J.J., Georgiopoulos M., Heileman G.L., Christodoulou C. Analogue circuit design and implementation of an adaptive resonance theory (ART) neural network architecture. International Journal of Electronics. 76(2):1994;271-291.
12. Sánchez-Sinencio E., Ramírez-Angulo J, Linares-Barranco B, Rodríguez-Vázquez A Operational transconductance amplifier-based nonlinear function synthesis. IEEE Journal of Solid-State Circuits. 24(6):1989;1576-1586.
13. Serrano-Gotarredona, T., & Linares-Barranco, B. (1996). A real-time clustering microchip neural engine. IEEE Transactions on VLSI Systems, accepted for publication.
14. Serrano-Gotarredona T., Linares-Barranco B., Huertas J.L. A CMOS VLSI analog current-mode high-speed ART 1 chip. Proceedings of the 1994 IEEE International Conference on Neural Networks (ICNN'94). 3:1994;1912-1916. Orlando, Florida.
15. Sheingold, D.H. (1976). Nonlinear circuits handbook. Norwood, MA: Analog Devices Inc.
16. Tsay S.W., Newcomb R.W. VLSI implementation of ART 1 memories. IEEE Transactions on Neural Networks. 2(2):1991;214-221. March.
17. Wunsch D.C. II, Caudell T.P., Capps C.D., Marks R.J. II, Falk R.A. An optoelectronic implementation of the adaptive resonance neural network. IEEE Transactions on Neural Networks. 4(4):1993;673-684. July.