Nature inspired optimization tools for SVMs - NIOTS

Support Vector Machines (SVMs) technique for achieving classifiers and regressors. However, to obtain models with high accuracy and low complexity, it is necessary to define the kernel parameters as well as the parameters of the training model, which are called hyperparameters. The challenge of defi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Carlos Eduardo da Silva Santos, Leandro dos Santos Coelho, Carlos Humberto Llanos
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Support vectors machines Parameters selection problem Adaptive parameters control Differential evolution algorithm Multi-objective optimization problem Science Q
Acceso en línea:	https://doaj.org/article/fabf074cb0ae4dbbb4b6ddd91194fe52
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fabf074cb0ae4dbbb4b6ddd91194fe52
record_format	dspace
spelling	oai:doaj.org-article:fabf074cb0ae4dbbb4b6ddd91194fe522021-11-12T04:35:29ZNature inspired optimization tools for SVMs - NIOTS2215-016110.1016/j.mex.2021.101574https://doaj.org/article/fabf074cb0ae4dbbb4b6ddd91194fe522021-01-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2215016121003642https://doaj.org/toc/2215-0161Support Vector Machines (SVMs) technique for achieving classifiers and regressors. However, to obtain models with high accuracy and low complexity, it is necessary to define the kernel parameters as well as the parameters of the training model, which are called hyperparameters. The challenge of defining the more suitable value to hyperparameters is called the Parameter Selection Problem (PSP). However, minimizing the complexity and maximizing the generalization capacity of the SVMs are conflicting criteria. Therefore, we propose the Nature Inspired Optimization Tools for SVMs (NIOTS) that offers a method to automate the search process for the best possible solution for the PSP, allowing the user to quickly obtain several sets of good solutions and choose the one most appropriate for his specific problem. • The PSP has been modeled as a Multiobjective Optimization Problem (MOP) with two objectives: (1) good precision and (2) low complexity (low number of support vectors). • The user can evaluate multiple solutions included in the Pareto front, in terms of precision and low complexity of the model. • Apart from the Adaptive Parameter with Mutant Tournament Multiobjective Differential Evolution (APMT-MODE), the user can choose other metaheuristics and also among several kernel options.Carlos Eduardo da Silva SantosLeandro dos Santos CoelhoCarlos Humberto LlanosElsevierarticleSupport vectors machinesParameters selection problemAdaptive parameters controlDifferential evolution algorithmMulti-objective optimization problemScienceQENMethodsX, Vol 8, Iss , Pp 101574- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Support vectors machines Parameters selection problem Adaptive parameters control Differential evolution algorithm Multi-objective optimization problem Science Q
spellingShingle	Support vectors machines Parameters selection problem Adaptive parameters control Differential evolution algorithm Multi-objective optimization problem Science Q Carlos Eduardo da Silva Santos Leandro dos Santos Coelho Carlos Humberto Llanos Nature inspired optimization tools for SVMs - NIOTS
description	Support Vector Machines (SVMs) technique for achieving classifiers and regressors. However, to obtain models with high accuracy and low complexity, it is necessary to define the kernel parameters as well as the parameters of the training model, which are called hyperparameters. The challenge of defining the more suitable value to hyperparameters is called the Parameter Selection Problem (PSP). However, minimizing the complexity and maximizing the generalization capacity of the SVMs are conflicting criteria. Therefore, we propose the Nature Inspired Optimization Tools for SVMs (NIOTS) that offers a method to automate the search process for the best possible solution for the PSP, allowing the user to quickly obtain several sets of good solutions and choose the one most appropriate for his specific problem. • The PSP has been modeled as a Multiobjective Optimization Problem (MOP) with two objectives: (1) good precision and (2) low complexity (low number of support vectors). • The user can evaluate multiple solutions included in the Pareto front, in terms of precision and low complexity of the model. • Apart from the Adaptive Parameter with Mutant Tournament Multiobjective Differential Evolution (APMT-MODE), the user can choose other metaheuristics and also among several kernel options.
format	article
author	Carlos Eduardo da Silva Santos Leandro dos Santos Coelho Carlos Humberto Llanos
author_facet	Carlos Eduardo da Silva Santos Leandro dos Santos Coelho Carlos Humberto Llanos
author_sort	Carlos Eduardo da Silva Santos
title	Nature inspired optimization tools for SVMs - NIOTS
title_short	Nature inspired optimization tools for SVMs - NIOTS
title_full	Nature inspired optimization tools for SVMs - NIOTS
title_fullStr	Nature inspired optimization tools for SVMs - NIOTS
title_full_unstemmed	Nature inspired optimization tools for SVMs - NIOTS
title_sort	nature inspired optimization tools for svms - niots
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/fabf074cb0ae4dbbb4b6ddd91194fe52
work_keys_str_mv	AT carloseduardodasilvasantos natureinspiredoptimizationtoolsforsvmsniots AT leandrodossantoscoelho natureinspiredoptimizationtoolsforsvmsniots AT carloshumbertollanos natureinspiredoptimizationtoolsforsvmsniots
_version_	1718431266291843072

Nature inspired optimization tools for SVMs - NIOTS

Ejemplares similares