This paper deals with the problem of identification of continuous time dynamic neural networks when the measurements are given only at discrete time moments, not necessarily uniformly distributed. It is shown that the modified adjoint system, generating the gradient of the performance index, is a continuous-time system with jumps of state variables at moments corresponding to moments of measurements.
CITATION STYLE
Fujarewicz, K., & Galuszka, A. (2004). Generalized backpropagation through time for continuous time neural networks and discrete time measurements. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3070, pp. 190–196). Springer Verlag. https://doi.org/10.1007/978-3-540-24844-6_24
Mendeley helps you to discover research relevant for your work.