Adjusting delays in a NARX neural network
4 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
S. Moore
el 19 de Feb. de 2015
Comentada: Greg Heath
el 23 de Feb. de 2015
The NARX provided by the MATLAB toolbox defines y(t) as a function of past inputs and outputs:
y(t) = f(x(t-1), ... ,x(t-d),y(t-1), ... ,y(t-d))
The standard definition of NARX defines y(t) as a function of past and present inputs and past outputs:
y(t) = f( x(t) ,x(t-1), ... ,x(t-d),y(t-1), ... ,y(t-d))
I have attached a picture to illustrate my question.
What is the MATLAB command to modify the input TDL of my existing NARX model to accomidate the present input?
My illustration shows [0:6], but any help is appreciated to achieve similar results such as [0:5], etc.
0 comentarios
Respuesta aceptada
Más respuestas (1)
Greg Heath
el 19 de Feb. de 2015
MATLAB Toolbox yields the standard dependence on the present input indicated by a 0 input delay. However, feedback delays must be positive.
Hope this helps.
Thank you for formally accepting my answer
Greg
2 comentarios
Greg Heath
el 23 de Feb. de 2015
I explained in my answer that the MATLAB software does support ID >= 0. However FD must be > 0.
In other words:
Software OK
Documentation LACKING
Greg
Ver también
Categorías
Más información sobre Nonlinear ARX Models en Help Center y File Exchange.
Productos
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!