Improving Neural Network Classification Using Further Division of Recognition Space

@inproceedings{Chen2008ImprovingNN,
  title={Improving Neural Network Classification Using Further Division of Recognition Space},
  author={Zhenxiang Chen and HaiYang Wang and Crina Grosan and Yuehui Chen and Lin Wang},
  year={2008}
}
Further Division of Recognition Space (FDRS) is a novel technique used for neural network classification. Recognition space is a space that is defined to categorize data sample after sample, which is mapped by neural network learning. It is divided manually into few parts to categorize samples, which can be considered as a line segment in the traditional neural network classification. In addition, the data recognition space is divided into many partitions, which will attach to different classes… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 18 references

Fumiaki, analysis on the robustness of the pressure-based individual identification system based on neural networks, international journal of innovative Computing, Information and Control

M. Lina
2007
View 1 Excerpt

A Novel Classification Method Based on Data Gravitation

2005 International Conference on Neural Networks and Brain • 2005
View 1 Excerpt

A pulsed neural network incorporating short term synaptic plasticity for engineering applications,international journal of innovative Computing, Information and Control

M. Makoto, K. Seiichi, H. Hironori
2005
View 1 Excerpt

Improvement of generalization ability for identifying dynamicsystems by using universal learning networks, Proceedings

Kim, S.-H, K. Hirasawa, J. Hu
IJCNN ’01. International Joint Conference on neural networks, • 2001
View 1 Excerpt

Improvement of neural network learning algorithm and itsapplication in control

W. Yan, S. Hongbao
Proc. the 3rd World Congress on neural networks, Hefei, Anhui, • 2000
View 1 Excerpt

The Nature of Statistical Learning Theory

Statistics for Engineering and Information Science • 2000
View 1 Excerpt

Similar Papers

Loading similar papers…