DocumentCode :
3111819
Title :
Learning of new neuron model based on geometric mean with new error metrics
Author :
Shiblee, Mohd ; Chandra, B. ; Kalra, Prem K.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol., Kanpur
fYear :
2008
fDate :
12-15 Oct. 2008
Firstpage :
1122
Lastpage :
1127
Abstract :
The paper proposes new neuron architecture for Neural Network models with an aggregation function based on geometric mean of all inputs. This new neuron model gives better accuracy compared to Multilayer Perceptron model (MLP) without increasing the number of parameters. Various error measures have been used with this model. The effectiveness of this model with different error measures have been illustrated on various data sets pertaining to classification, prediction and approximations problems.
Keywords :
approximation theory; error statistics; neural nets; error metrics; geometric mean; multilayer perceptron model; neural network models; neuron model; paper neuron architecture; Arithmetic; Backpropagation algorithms; Industrial engineering; Mathematical model; Multilayer perceptrons; Neural networks; Neurons; Paper technology; Solid modeling; Technology management; Classification; Functional Approximation; Generalized Harmonic and Geometric Errors; Geometric Mean; Neuron model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man and Cybernetics, 2008. SMC 2008. IEEE International Conference on
Conference_Location :
Singapore
ISSN :
1062-922X
Print_ISBN :
978-1-4244-2383-5
Electronic_ISBN :
1062-922X
Type :
conf
DOI :
10.1109/ICSMC.2008.4811432
Filename :
4811432
Link To Document :
بازگشت