Observatorio de I+D+i UPM

Memorias de investigación
Research Publications in journals:
Multilayered neural architectures evolution for computing sequences of orthogonal polynomials
Year:2018
Research Areas
  • Artificial intelligence
Information
Abstract
This article presents an evolutionary algorithm to autonomously construct full-connected multilayered feedforward neural architectures. This algorithm employs grammar-guided genetic programming with a context-free grammar that has been specifically designed to satisfy three important restrictions. First, the sentences that belong to the language produced bythe grammar only encode all valid neural architectures. Second, full-connected feedforwardneural architectures of any size can be generated. Third, smaller-sized neural architecturesare favored to avoid overfitting. The proposed evolutionary neural architectures construction system is applied to compute the terms of the two sequences that define the three-term recurrence relation associated with a sequence of orthogonal polynomials. This application imposes an important constraint: training datasets are always very small. Therefore, an adequate sized neural architecture has to be evolved to achieve satisfactory results, which arepresented in terms of accuracy and size of the evolved neural architectures, and convergencespeed of the evolutionary process.
International
Si
JCR
Si
Title
Annals of Mathematics And Artificial Intelligence
ISBN
1012-2443
Impact factor JCR
0,899
Impact info
Datos JCR del año 2017
Volume
84
10.1007/s10472-018-9601-2
Journal number
3-4
From page
161
To page
184
Month
DICIEMBRE
Ranking
Participants
  • Autor: Maria Dolores Barrios Rolania (UPM)
  • Autor: Guillermo Delgado Martínez (UPM)
  • Autor: Daniel Manrique Gamo (UPM)
Research Group, Departaments and Institutes related
  • Creador: Departamento: Inteligencia Artificial
S2i 2020 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)