Loading...
Loading...

Go to the content (press return)

LTI ODE-valued neural networks

Author
Velasco, M.; Martin, E.X.; Angulo, C.; Marti, P.
Type of activity
Journal article
Journal
Applied intelligence
Date of publication
2014-05
Volume
41
Number
2
First page
594
Last page
605
DOI
https://doi.org/10.1007/s10489-014-0548-7 Open in new window
Project funding
Event-Driven Embedded and Networked Control Systems, CICYT DPI2010-18601
PATRICIA. TIN2012-38416-C03-01
Repository
http://hdl.handle.net/2117/24573 Open in new window
URL
http://link.springer.com/article/10.1007/s10489-014-0548-7 Open in new window
Abstract
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...
Citation
Velasco, M. [et al.]. LTI ODE-valued neural networks. "Applied intelligence", Maig 2014, vol. 41, núm. 2, p. 594-605.
Keywords
Complex-valued neural network, Dynamical neural network, Parallel problem solving
Group of research
CREB - Biomedical Engineering Research Centre
GREC - Knowledge Engineering Research Group
GRINS - Intelligent Robots and Systems
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants