Feature extraction for deep neural networks based on decision boundaries

Seongyoun Woo; Chulhee Lee

doi:10.1117/12.2263172

1 May 2017 Feature extraction for deep neural networks based on decision boundaries

Seongyoun Woo, Chulhee Lee

Proceedings Volume 10203, Pattern Recognition and Tracking XXVIII; 1020306 (2017) https://doi.org/10.1117/12.2263172
Event: SPIE Defense + Security, 2017, Anaheim, CA, United States

Abstract

Feature extraction is a process used to reduce data dimensions using various transforms while preserving the discriminant characteristics of the original data. Feature extraction has been an important issue in pattern recognition since it can reduce the computational complexity and provide a simplified classifier. In particular, linear feature extraction has been widely used. This method applies a linear transform to the original data to reduce the data dimensions. The decision boundary feature extraction method (DBFE) retains only informative directions for discriminating among the classes. DBFE has been applied to various parametric and non-parametric classifiers, which include the Gaussian maximum likelihood classifier (GML), the k-nearest neighbor classifier, support vector machines (SVM) and neural networks. In this paper, we apply DBFE to deep neural networks. This algorithm is based on the nonparametric version of DBFE, which was developed for neural networks. Experimental results with the UCI database show improved classification accuracy with reduced dimensionality.

Citation Download Citation

Seongyoun Woo and Chulhee Lee "Feature extraction for deep neural networks based on decision boundaries", Proc. SPIE 10203, Pattern Recognition and Tracking XXVIII, 1020306 (1 May 2017); https://doi.org/10.1117/12.2263172

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