Carregant...
Carregant...

Vés al contingut (premeu Retorn)

LTI ODE-valued neural networks

Autor
Velasco, M.; Martin, E.X.; Angulo, C.; Marti, P.
Tipus d'activitat
Article en revista
Revista
Applied intelligence
Data de publicació
2014-05
Volum
41
Número
2
Pàgina inicial
594
Pàgina final
605
DOI
https://doi.org/10.1007/s10489-014-0548-7 Obrir en finestra nova
Projecte finançador
Event-Driven Embedded and Networked Control Systems, CICYT DPI2010-18601
PATRICIA. TIN2012-38416-C03-01
Repositori
http://hdl.handle.net/2117/24573 Obrir en finestra nova
URL
http://link.springer.com/article/10.1007/s10489-014-0548-7 Obrir en finestra nova
Resum
A dynamical version of the classical McCulloch & Pitts’ neural model is introduced in this paper. In this new approach, artificial neurons are characterized by: i) inputs in the form of differentiable continuous-time signals, ii) linear time-invariant ordinary differential equations (LTI ODE) for connection weights, and iii) activation functions evaluated in the frequency domain. It will be shown that this new characterization of the constitutive nodes in an artificial neural network, namely L...
Citació
Velasco, M. [et al.]. LTI ODE-valued neural networks. "Applied intelligence", Maig 2014, vol. 41, núm. 2, p. 594-605.
Paraules clau
Complex-valued neural network, Dynamical neural network, Parallel problem solving
Grup de recerca
CREB - Centre de Recerca en Enginyeria Biomedica
GREC - Grup de Recerca en Enginyeria del Coneixement
GRINS - Grup de Recerca en Robòtica Intel·ligent i Sistemes
IDEAI-UPC Intelligent Data Science and Artificial Intelligence

Participants