DocumentCode :
469275
Title :
A Novel Method to Measure the Learning Capability of a Parameter in Artificial Neural Network with Application to Network Freezing
Author :
Urolagin, Siddhaling ; Prema, K.V. ; Reddy, N. V Subba
Author_Institution :
M.I.T., Manipal
Volume :
1
fYear :
2007
fDate :
13-15 Dec. 2007
Firstpage :
242
Lastpage :
249
Abstract :
The artificial neural network is typically trained from initial weight/bias position. As training progresses the network parameters such as weights and biases are updated according to learning algorithm to reduce the performance index. Not all the network parameters are equally learning the input-output mapping. Some parameters would hold more discriminating capability while others are not so effective. We propose a novel method of measuring the learning capability of a network parameter. The learning capability for a parameter we call it as learnability is contribution of that parameter to reduce performance index as the network is training. The proposed method of measuring learnability is applied on network parameters freezing on feedforward neural network. Our method is validated on MNIST handwritten numeral database using backpropagation learning algorithm.
Keywords :
backpropagation; feedforward neural nets; MNIST handwritten numeral database; artificial neural network training; backpropagation learning algorithm; feedforward neural network; input-output mapping; learnability measuring; learning capability; network freezing; network parameters freezing; performance index; Algorithm design and analysis; Artificial neural networks; Computational efficiency; Computational intelligence; Computer architecture; Convergence; Feedforward neural networks; Neural networks; Neurons; Performance analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Conference on Computational Intelligence and Multimedia Applications, 2007. International Conference on
Conference_Location :
Sivakasi, Tamil Nadu
Print_ISBN :
0-7695-3050-8
Type :
conf
DOI :
10.1109/ICCIMA.2007.98
Filename :
4426587
Link To Document :
بازگشت