Add to ORKGAbstract In this paper we extend the models discussed by Cohen (1992) by introducing an input term. This allows the resulting models to be utilized for system identification tasks. We prove that this model is stable in the sense that a bounded input leads to a bounded state when a minor restriction is imposed on the Lyapunov function. By employing this stability result, we are able to find a learning algorithm which guarantees convergence to a set of parameters for which the error between the model trajectories and the desired trajectories vanish.University of New Mexic
In this paper we discuss PAC-learning of functions from a traditional system identification perspect...
This thesis is concerned with a method to automatically identify parameters of an unknown or changin...
Linear programming methods for discrete l1 approximation are used to provide solutions to problems o...
In this paper we extend the models discussed by Cohen (1992) by introducing an input term. This allo...
In this paper, we present an approach to system identification based on viewing identification as a ...
The process of model learning can be considered in two stages: model selection and parameter estimat...
A dynamical process is modelled by a system of non-linearizable ordinary differential equations with...
In this letter, we develop a new adjustment rule for a perceptron with a saturating nonlinearity tha...
This paper presents a set of single layer low complexity nonlinear adaptive models for efficient ide...
The problem of system identification is to learn the system dynamics from data. While classical syst...
The paper presents two learning methods for nonlinear system identification. Both methods employ neu...
This paper deals with studying the asymptotical properties of multilayer neural networks models used...
In this paper, based on the deterministic learning mechanism, we present an alternative systematic s...
In system identification, one usually cares most about finding a model whose outputs are as close as...
This thesis contains three parts. In the first part, a set-membership identification algorithm is de...
In this paper we discuss PAC-learning of functions from a traditional system identification perspect...
This thesis is concerned with a method to automatically identify parameters of an unknown or changin...
Linear programming methods for discrete l1 approximation are used to provide solutions to problems o...
In this paper we extend the models discussed by Cohen (1992) by introducing an input term. This allo...
In this paper, we present an approach to system identification based on viewing identification as a ...
The process of model learning can be considered in two stages: model selection and parameter estimat...
A dynamical process is modelled by a system of non-linearizable ordinary differential equations with...
In this letter, we develop a new adjustment rule for a perceptron with a saturating nonlinearity tha...
This paper presents a set of single layer low complexity nonlinear adaptive models for efficient ide...
The problem of system identification is to learn the system dynamics from data. While classical syst...
The paper presents two learning methods for nonlinear system identification. Both methods employ neu...
This paper deals with studying the asymptotical properties of multilayer neural networks models used...
In this paper, based on the deterministic learning mechanism, we present an alternative systematic s...
In system identification, one usually cares most about finding a model whose outputs are as close as...
This thesis contains three parts. In the first part, a set-membership identification algorithm is de...
In this paper we discuss PAC-learning of functions from a traditional system identification perspect...
This thesis is concerned with a method to automatically identify parameters of an unknown or changin...
Linear programming methods for discrete l1 approximation are used to provide solutions to problems o...