A study on learning mechanism for neuron networks with weight-function

Xi Huang; Zong-huang Weng; Wen-zao Shi; Ping Wang

doi:10.1117/12.2013811

13 March 2013 A study on learning mechanism for neuron networks with weight-function

Xi Huang, Zong-huang Weng, Wen-zao Shi, Ping Wang

Proceedings Volume 8784, Fifth International Conference on Machine Vision (ICMV 2012): Algorithms, Pattern Recognition, and Basic Technologies; 87840L (2013) https://doi.org/10.1117/12.2013811
Event: Fifth International Conference on Machine Vision (ICMV 12), 2012, Wuhan, China

Abstract

In this paper a new neural network model with weight-function is proposed. In the model, the weight is a function with adjustable parameters, and the sum of these weight functions as the neuron output. And according to BP algorithm, the learning algorithm of feed-forward neural network with weight-function neurons is studied. Simulation results show that, applying the back-propagation algorithm to the new neural network the better convergence rate can be obtained and in some applications the new neural network based on the weight-function neurons is superior to the BP network based on the MP neuron model, so that it has a significant value in further research and application.

Citation Download Citation

Xi Huang, Zong-huang Weng, Wen-zao Shi, and Ping Wang "A study on learning mechanism for neuron networks with weight-function", Proc. SPIE 8784, Fifth International Conference on Machine Vision (ICMV 2012): Algorithms, Pattern Recognition, and Basic Technologies, 87840L (13 March 2013); https://doi.org/10.1117/12.2013811

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available