Designing partially-connected, multilayer perceptron neural nets through information gain

Rodriguez Salas D, Gómez-Gil P, Olvera-López A (2013)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2013

Edited Volumes: Proceedings of the International Joint Conference on Neural Networks

Pages Range: 1-5

Conference Proceedings Title: The 2013 International Joint Conference on Neural Networks (IJCNN)

Event location: Dallas, TX, USA US

ISBN: 9781467361293

URI: http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Dalia13-PcMLP.pdf

DOI: 10.1109/IJCNN.2013.6706991

Abstract

An adequate number of hidden neurons and connection structure of a multi-layer perceptron network (MLP) are usually determined by experimentation. In this paper, we propose a scheme to define an appropriate structure and number of neurons of a partially connected MLP when used for classification. Rules for designing the network are based on a decision tree previously built using information gain. Our structure, called IG Net, is inspired by the Entropy Net [1], but contains fewer layers and connections than such network or than a fully-connected neural network and holds equivalent classification power. We tested the classification performance of our network using 10 databases from the UCI Machine Learning Repository. The performance obtained by IG Net using such databases showed to be statistically equivalent to the one obtained by an Entropy Net or by a fully-connected MLP, using fewer computational resources than the compared models. © 2013 IEEE.

Authors with CRIS profile

Dalia Rodriguez Salas Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

Benemérita Universidad Autónoma de Puebla (BUAP) / Meritorious Autonomous University of Puebla MX Mexico (MX) National Institute of Astrophysics, Optics and Electronics / Instituto Nacional de Astrofísica, Óptica y Electrónica (INAOE) MX Mexico (MX)

How to cite

APA:

Rodriguez Salas, D., Gómez-Gil, P., & Olvera-López, A. (2013). Designing partially-connected, multilayer perceptron neural nets through information gain. In The 2013 International Joint Conference on Neural Networks (IJCNN) (pp. 1-5). Dallas, TX, USA, US.

MLA:

Rodriguez Salas, Dalia, Pilar Gómez-Gil, and Arturo Olvera-López. "Designing partially-connected, multilayer perceptron neural nets through information gain." Proceedings of the The 2013 International Joint Conference on Neural Networks (IJCNN), Dallas, TX, USA 2013. 1-5.

BibTeX: Download