Abstract
In this paper, the design methodology of neural network hardware has been discussed, and two weighted neural network implemented by this method been applied for object recognition. It was pointed out that the main problem of the two weighted neural network hardware implementation lies in three aspects. At final, two weighted neural network implemented by this method is applied for object recognition, and the algorithm were presented. We did experiments on recognition of omnidirectionally oriented rigid objects on the same level, using the two weighted neural networks. Many animal and vehicle models (even with rather similar shapes) were recognized omnidirectionally thousands of times. For total 8800 tests, the correct recognition rate is 98.75%, the error rate and the rejection rate are 0.5 and 1.25% respectively.
Chapter PDF
Similar content being viewed by others
References
Wang ShouJue etc. “Discussion on the Basic Mathematical Models of Neurons in General Purpose Neurocomputer”. ACTA ELECTRONICA SINICA, Vol.29 No.5, 2001
Wang Shoujue etc. The Sequential Learning Ahead Masking (SLAM) model of neural networks for pattern classification. Proceedings of JCIS98. Vol.IV, pp199–202. Oct. 1998. RTP. NC. USA
Wang Shoujue. Priority Ordered Neural Networks with Better Similarity to Human knowledge Representation. Chinese Journal Of Electronics. Vol.8. No.1, pp. 1–4. 1999
Cao yu, Two weighted neural network approach, Master thesis, Institute of Semiconductors, CAS, 2002
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 International Federation for Information Processing
About this paper
Cite this paper
Cao, W., Lu, F., Xiao, G., Wang, S. (2005). Hardware Design of Two Weighted Neural Network and Application for Object Recognition. In: Shi, Z., He, Q. (eds) Intelligent Information Processing II. IIP 2004. IFIP International Federation for Information Processing, vol 163. Springer, Boston, MA. https://doi.org/10.1007/0-387-23152-8_64
Download citation
DOI: https://doi.org/10.1007/0-387-23152-8_64
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-23151-8
Online ISBN: 978-0-387-23152-5
eBook Packages: Computer ScienceComputer Science (R0)