Extended evaluation of the Volterra-Neural Network for model compression

When large models are used for a classification task, model compression is necessary because there are transmission, space, time or computing constraints that have to be fulfilled. Multilayer Perceptron (MLP) models are traditionally used as a classifier, but depending on the problem, they may need...

Descripción completa

Detalles Bibliográficos
Autor principal: Rubiolo, Mariano
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2012
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/123741
https://41jaiio.sadio.org.ar/sites/default/files/14_ASAI_2012.pdf
Aporte de:SEDICI (UNLP) de Universidad Nacional de La Plata Ver origen
Descripción
Sumario:When large models are used for a classification task, model compression is necessary because there are transmission, space, time or computing constraints that have to be fulfilled. Multilayer Perceptron (MLP) models are traditionally used as a classifier, but depending on the problem, they may need a large number of parameters (neuron functions, weights and bias) to obtain an acceptable performance. This work extends the evaluation of a technique to compress an array of MLPs, through the outputs of a Volterra-Neural Network (Volterra-NN), maintaining its classification performance. The obtained results show that these outputs can be used to build an array of (Volterra-NN) that needs significantly less parameters than the original array of MLPs, furthermore having the same high accuracy in most of the cases. The Volterra-NN compression capabilities have been tested by solving several kind of classification problems. Experimental results are presented on three well-known databases: Letter Recognition, Pen-Based Recognition of Handwritten Digits, and Face recognition databases.