Empirical estimation of generalization ability of neural networks

Dilip Sarkar

doi:10.1117/12.235979

22 March 1996 Empirical estimation of generalization ability of neural networks

Dilip Sarkar

Proceedings Volume 2760, Applications and Science of Artificial Neural Networks II; (1996) https://doi.org/10.1117/12.235979
Event: Aerospace/Defense Sensing and Controls, 1996, Orlando, FL, United States

Abstract

This work concentrates on a novel method for empirical estimation of generalization ability of neural networks. Given a set of training (and testing) data, one can choose a network architecture (number of layers, number of neurons in each layer etc.), an initialization method, and a learning algorithm to obtain a network. One measure of performance of the trained network is how closely its actual output approximates the desired output for an input that it has never seen before. Current methods provide a `number' that indicates the estimation of generalization ability of the network. However, this number provides no further information to understand the contributing factors when generalization stability is not very good. The proposed method uses a number of parameters to define generalization ability. A set of values of these parameters provides an estimate of generalization ability. In addition, a value of each parameter indicate the contribution of such factors as network architecture, initialization method, and training data set etc. Furthermore, a method has been developed to verify the validity of estimated values of the parameters.

Citation Download Citation

Dilip Sarkar "Empirical estimation of generalization ability of neural networks", Proc. SPIE 2760, Applications and Science of Artificial Neural Networks II, (22 March 1996); https://doi.org/10.1117/12.235979

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