Experimental approach for the evaluation of neural network classifier algorithms

Masoud Ghaffari; Ernest L. Hall

doi:10.1117/12.515826

30 September 2003 Experimental approach for the evaluation of neural network classifier algorithms

Masoud Ghaffari, Ernest L. Hall

Proceedings Volume 5267, Intelligent Robots and Computer Vision XXI: Algorithms, Techniques, and Active Vision; (2003) https://doi.org/10.1117/12.515826
Event: Photonics Technologies for Robotics, Automation, and Manufacturing, 2003, Providence, RI, United States

Abstract

The purpose of this paper is to demonstrate a new benchmark for comparing the rate of convergence in neural network classification algorithms. The benchmark produces datasets with controllable complexity that can be used to test an algorithm. The dataset generator uses the concept of random numbers and linear normalization to generate the data. In a case of a one-layer perceptron, the output datasets are sensitive to weight or bias of the perceptron. A Matlab implemented algorithm analyzed the sample datasets and the benchmark results. The results demonstrate that the convergence time varies based on some selected specifications of the generated dataset. This benchmark and the generated datasets can be used by researchers that work on neural network algorithms and are looking for a straightforward and flexible dataset to examine and evaluate the efficiency of neural network classification algorithms.

Citation Download Citation

Masoud Ghaffari and Ernest L. Hall "Experimental approach for the evaluation of neural network classifier algorithms", Proc. SPIE 5267, Intelligent Robots and Computer Vision XXI: Algorithms, Techniques, and Active Vision, (30 September 2003); https://doi.org/10.1117/12.515826

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