DocumentCode :
3010509
Title :
A Pattern Recognition Neural Network Using Many Sets of Weights and Biases
Author :
Dung, Le ; Mizukawa, Makoto
Author_Institution :
Shibaura Inst. of Technol., Tokyo
fYear :
2007
fDate :
20-23 June 2007
Firstpage :
285
Lastpage :
290
Abstract :
In supervised training, we often try to find out a set of weights and biases for a pattern recognition neural network in order to classify all patterns in a training data set. However, it would be difficult if the neural network was not big enough for learning a large training data set. In this paper, we propose a training method and a design of pattern recognition neural network that is not big but still able to classify all the training patterns exactly. The neural network is designed with a reject output to separate the training data set into some parts for classifying more easily. The training method helps the neural network to find out not only one but many sets of weights and biases for classifying all the training patterns, controlling the recognizing rejection and reducing the error rate. On the other hand, with this design we can reduce the size of the neural network implemented on a FPGA chip in order to make fast smart sensors for the robots.
Keywords :
field programmable gate arrays; intelligent sensors; learning (artificial intelligence); microprocessor chips; neural nets; pattern classification; robots; AI learning; FPGA chip; neural network design; pattern classification; pattern recognition; robot; smart sensor; supervised training; Computational intelligence; Error analysis; Field programmable gate arrays; Neural networks; Neurons; Pattern recognition; Robotics and automation; Shape; Space technology; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence in Robotics and Automation, 2007. CIRA 2007. International Symposium on
Conference_Location :
Jacksonville, FI
Print_ISBN :
1-4244-0790-7
Electronic_ISBN :
1-4244-0790-7
Type :
conf
DOI :
10.1109/CIRA.2007.382856
Filename :
4269856
Link To Document :
بازگشت