Sciweavers

160 search results - page 6 / 32
» A Very Fast Learning Method for Neural Networks Based on Sen...
Sort
View
PR
2007
118views more  PR 2007»
13 years 7 months ago
A cooperative constructive method for neural networks for pattern recognition
In this paper, we propose a new constructive method, based on cooperative coevolution, for designing automatically the structure of a neural network for classification. Our appro...
Nicolás García-Pedrajas, Domingo Ort...
ESANN
2004
13 years 9 months ago
Neural methods for non-standard data
Standard pattern recognition provides effective and noise-tolerant tools for machine learning tasks; however, most approaches only deal with real vectors of a finite and fixed dime...
Barbara Hammer, Brijnesh J. Jain
ISQED
2007
IEEE
127views Hardware» more  ISQED 2007»
14 years 1 months ago
Sensitivity Based Link Insertion for Variation Tolerant Clock Network Synthesis
Clock distribution is one of the key limiting factors in any high speed, sub-100nm VLSI design. Unwanted clock skews, caused by variation effects like manufacturing variations, po...
Joon-Sung Yang, Anand Rajaram, Ninghy Shi, Jian Ch...
IJON
2006
112views more  IJON 2006»
13 years 7 months ago
Palmprint recognition using FastICA algorithm and radial basis probabilistic neural network
This paper proposes a novel and successful method for recognizing palmprint based on radial basis probabilistic neural network (RBPNN) proposed by us. The RBPNN is trained by the ...
Li Shang, De-Shuang Huang, Ji-Xiang Du, Chun-Hou Z...
NN
2006
Springer
108views Neural Networks» more  NN 2006»
13 years 7 months ago
Performance analysis of LVQ algorithms: A statistical physics approach
Learning vector quantization (LVQ) constitutes a powerful and intuitive method for adaptive nearest prototype classification. However, original LVQ has been introduced based on he...
Anarta Ghosh, Michael Biehl, Barbara Hammer