Fast implementation of neural network classification

Guiwon Seo; Jiheon Ok; Chulhee Lee

doi:10.1117/12.2026666

24 September 2013 Fast implementation of neural network classification

Guiwon Seo, Jiheon Ok, Chulhee Lee

Proceedings Volume 8871, Satellite Data Compression, Communications, and Processing IX; 887107 (2013) https://doi.org/10.1117/12.2026666
Event: SPIE Optical Engineering + Applications, 2013, San Diego, California, United States

Abstract

Most artificial neural networks use a nonlinear activation function that includes sigmoid and hyperbolic tangent functions. Most artificial networks employ nonlinear functions such as these sigmoid and hyperbolic tangent functions, which incur high complexity costs, particularly during hardware implementation. In this paper, we propose new polynomial approximation methods for nonlinear activation functions that can substantially reduce complexity without sacrificing performance. The proposed approximation methods were applied to pattern classification problems. Experimental results show that the processing time was reduced by up to 50% without any performance degradations in terms of computer simulation.

Citation Download Citation

Guiwon Seo, Jiheon Ok, and Chulhee Lee "Fast implementation of neural network classification", Proc. SPIE 8871, Satellite Data Compression, Communications, and Processing IX, 887107 (24 September 2013); https://doi.org/10.1117/12.2026666

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