The application of optimal weights initialization algorithm based on K-L transform in multi-layer perceptron networks

Wei Xiao; Dun Pu; Zhicheng Dong; Cungen Liu

doi:10.1117/12.2031954

19 July 2013 The application of optimal weights initialization algorithm based on K-L transform in multi-layer perceptron networks

Wei Xiao, Dun Pu, Zhicheng Dong, Cungen Liu

Author Affiliations +

Proceedings Volume 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013); 88784O (2013) https://doi.org/10.1117/12.2031954
Event: Fifth International Conference on Digital Image Processing, 2013, Beijing, China

Abstract

The paper presents a novel method of initial weights optimization method in Multi-Layer Perceptron Network(MLPN). Firstly, the sample sets should be transformed by K-L Transform. Secondly, use K-L Converting Matrix to initialize the weights between input and hidden layer. Thirdly the MLPN is trained by BP algorithm, and the convergence speed of MLPN is improved evidently. The ultimate test shows the new algorithm is suitable for the situation of low-dimensional data.

Citation Download Citation

Wei Xiao, Dun Pu, Zhicheng Dong, and Cungen Liu "The application of optimal weights initialization algorithm based on K-L transform in multi-layer perceptron networks", Proc. SPIE 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013), 88784O (19 July 2013); https://doi.org/10.1117/12.2031954

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