DocumentCode :
840600
Title :
Comparing Support Vector Machines and Feedforward Neural Networks With Similar Hidden-Layer Weights
Author :
Romero, E. ; Toppo, D.
Author_Institution :
Univ. Politecnica de Catalunya, Barcelona
Volume :
18
Issue :
3
fYear :
2007
fDate :
5/1/2007 12:00:00 AM
Firstpage :
959
Lastpage :
963
Abstract :
Support vector machines (SVMs) usually need a large number of support vectors to form their output. Recently, several models have been proposed to build SVMs with a small number of basis functions, maintaining the property that their hidden-layer weights are a subset of the data (the support vectors). This property is also present in some algorithms for feedforward neural networks (FNNs) that construct the network sequentially, leading to sparse models where the number of hidden units can be explicitly controlled. An experimental study on several benchmark data sets, comparing SVMs and the aforementioned sequential FNNs, was carried out. The experiments were performed in the same conditions for all the models, and they can be seen as a comparison of SVMs and FNNs when both models are restricted to use similar hidden-layer weights. Accuracies were found to be very similar. Regarding the number of support vectors, sequential FNNs constructed models with less hidden units than standard SVMs and in the same range as "sparse" SVMs. Computational times were lower for SVMs
Keywords :
feedforward neural nets; support vector machines; basis functions; feedforward neural networks; sequential FNN; similar hidden-layer weights; sparse models; support vector machines; Constraint optimization; Feedforward neural networks; Fuzzy control; Kernel; Machine learning; Neural networks; Support vector machine classification; Support vector machines; Feedforward neural networks (FNNs); sparse models; support vector machines (SVMs); Algorithms; Artificial Intelligence; Computer Simulation; Feedback; Information Storage and Retrieval; Models, Statistical; Neural Networks (Computer);
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/TNN.2007.891656
Filename :
4182404
Link To Document :
بازگشت