EFFICIENT FPGA IMPLEMENTATION OF A GENERIC FUNCTION APPROXIMATOR AND ITS APPLICATION TO NEURAL NET COMPUTATION

Midwest Symposium on Circuits and Systems

Volumn 2, Issue , 2003, Pages 843-846

  Bharkhada, Bharat Kishore ^a   Hauser, James ^b   Purdy, Carla ^a  

^a 705 Engineering Research Center   (United States)

^b NORTHERN KENTUCKY UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

FIELD PROGRAMMABLE GATE ARRAYS (FPGA); GENETIC ALGORITHMS; SYSTEM-ON-CHIP;

FPGA IMPLEMENTATIONS; FPGAS IMPLEMENTATION; FUNCTION APPROXIMATORS; GENERIC FUNCTIONS; HIGHLY ACCURATE; ITS APPLICATIONS; MEMORY EFFICIENT; MEMORY REQUIREMENTS; RECONFIGURABLE; SIGMOIDS;

NEURAL NETWORKS;

EID: 70450014917     PISSN: 15483746     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/MWSCAS.2003.1562418     Document Type: Conference Paper

References (12)

1. Hauser, J., Approximation of Nonlinear Functions for Fixed-Point and ASIC Applications Using a Genetic Algorithm, Doctoral Thesis, ECECS Department, University of Cincinnati, 2001.
2. Kothari, R., and Agyepong, K., On Lateral Connections in Fccd-Forwnrd Neural Networks, Proc. IEEE International Conference on Neural Networks (ICNN), pp. 13-18, 1996.
3. Zhno, M., FPGA-bnscd Simulation for Lateral I eed-loi ward Neural Networks, M.S. Thesis, ECECS Dcpt., University of Cincinnati. 2000.
4. Guccionc, S. A., and Gonzalez, M. J., A Neural Network Implementation Using Reconfigurabb Architectures, More FPGAs, W Moore and W.L Abingdon. Eds., EE&CS Books, Abingdon, England, pp. 443-45, 1993
5. Peng, W., Brugge, M., Nijhuis, J., and Spannenburg, L., Mapping a Trained Neural Network on Hardware, Soft Computing Symposium, 1999.
6. Leon, A. M.A., Castro, R. A., and Ascencio, L.R.R, An Artificial Neural Network On A Field Programmable Gate Array As A Virtual Sensor, Third International Workshop on Design of Mixed-Mode Integrated Circuits and Applications, Puerto Vallarta, Mexico, pp. 114-117, July 1999.
7. Sammut, K. M„ and Jones, S. R., Implementing Non Linear Activation Functions In Neural Network Emulators., Elect. Letters. 27 (12), 1991
8. Zohdy, U.S., and Al-Nsour, M., Implementation of Programmable Digital Sigmoid Function Circuit for Neuro-Computing, Proceedings of IEEE Midwest Symposium on Circuits and Systems, pp. 571-574, August 1998
9. rd November 1989.
10. Alippi, C, and Gajani, G.S., Simple Approximation of Sigmoidal Function: Realistic Design of Digital Neural Networks Capable of Learning, International Symposium on Circuits and Systems IEEE-ISCAS. Singapore, pp, 1505-1508., June 1991.
11. Hernandez, M.L.G., Ascensio, R.R.L., and Galicia, C.A, An Artificial Neural Network on a Complex Programmable Device as a Virtual Sensor Proceedings of the International Symposium on Robotics and Automation ISRA'98, Saltillo, Coahuila, Mexico, December 1998.
12. th March 2000.