Abstract
The probabilistic neural network (PNN) is one of the most promising neural networks, and is now applied to some real-world applications. In order to speed up the PNN calculation considerably, we have developed a PNN hardware system for video image recognition. The performance of the PNN hardware cannot be evaluated precisely until the evaluation system is completed. In this study, we developed a performance evaluation system for the PNN hardware and demonstrated it using the developed evaluation system.
Similar content being viewed by others
References
Specht DF (1990) Probabilistic neural networks. J Neural Networ 3:109–118
Specht DF (1990) Probabilistic neural networks and the polynomial adeline as complementary techniques for classification. IEEE Trans Neural Networ 1:111–110
Tian B, Azimi-Sadjadi MR, Vonder Haar TH, et al. (2000) Temporal updating scheme for probabilistic neural network with application on satellite cloud classification. IEEE Trans Neural Networ 11:903–920
Tian B, Azimi-Sadjadi MR (2001) Comparison of two different PNN training approaches for satellite cloud data classification. IEEE Trans Neural Networ 12:164–168
Mao KZ, Tan K-C, Ser W (2000) Probabilistic neural-network structure determination for pattern classification. IEEE Trans Neural Networ 11:1009–1016
Mizuno R, Aibe N, Yasunaga M, et al. (2003) Reconfigurable architecture for probabilistic neural network system. Proceedings of IEEE International Conference on Field-Programmable Technology (ICFPT) 2003, Tokyo, 15–17 December, pp 367–370
Aibe N, Yasunaga M, Yoshihara I, et al. (2002) A probabilistic neural network hardware system using a learning-parameter parallel architecture. Proceedings of IJCNN 2002 on IEEE WCCI 2002, CD-ROM, Honolulu, May 11-17
Aibe N, Yasunaga M, Yoshihara I (2001) Self-learning probabilistic neural network hardware using reconfigurable LSIs. Proceedings of Artificial Life and Robotics (AROB) 6th ’01 Tokyo, Japan, Jan 15-17, 1:89–92
Aibe N, Yasunaga M (2002) An architecture for parallelized highspeed probabilistic neural network calculation and its application to image recognition systems. Information Processing Society of Japan (IPSJ) Trans High Performance Computing Systems (HPS) 43:206–218
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented, in part, at the 8th International Symposium on Artificial Life and Robotics, Oita, Japan, January 24#x2013;26, 2003
About this article
Cite this article
Aibe, N., Mizuno, R., Nakamura, M. et al. Performance evaluation system for probabilistic neural network hardware. Artif Life Robotics 8, 208–213 (2004). https://doi.org/10.1007/s10015-004-0309-5
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10015-004-0309-5