Learning dynamical systems in a stationary environment
نویسنده
چکیده
We consider the problem of learning the input–output relation of a dynamical system from noisy data. Our method rests on the use of a smooth simultaneous estimator which generalizes the standard empirical estimator. In a stationary environment, our algorithm is shown to select a model which exhibits the Probably Approximately Correct (PAC) property under very mild conditions. This contribution should be thought of as a rst attempt to extend concepts developed in learning theory to the eld of system identi cation where, due to the presence of the system dynamics, the typical i.i.d. assumption on the data made in learning theory is not satis ed. c © 1998 Elsevier Science B.V. All rights reserved.
منابع مشابه
A-Life Based Optimisation of Non-Stationary Dynamical Systems
In this paper, we develop an intelligent system to approach dynamical optimisation problems emerging in control of complex systems. In particular our proposal is to exploit the adaptivity of an artificial life (alife) environment in order to achieve "not control rules but autonomous structures able to dynamically adapt and to generate optimised-control rules". The basic features of the proposed...
متن کاملOn-line learning and modulation of periodic movements with nonlinear dynamical systems
The paper presents a two-layered system for (1) learning and encoding a periodic signal without any knowledge on its frequency and waveform, and (2) modulating the learned periodic trajectory in response to external events. The system is used to learn periodic tasks on a humanoid HOAP-2 robot. The first layer of the system is a dynamical system responsible for extracting the fundamental frequen...
متن کاملDynamically analyzing cell interactions in biological environments using multiagent social learning framework
BACKGROUND Biological environment is uncertain and its dynamic is similar to the multiagent environment, thus the research results of the multiagent system area can provide valuable insights to the understanding of biology and are of great significance for the study of biology. Learning in a multiagent environment is highly dynamic since the environment is not stationary anymore and each agent'...
متن کاملDynamical system for learning the waveform and frequency of periodic signals – application to drumming
The paper presents a two-layered system for learning and encoding a periodic signal and its application to a drumming task. The two layers are the dynamical system responsible for extracting the main frequency of the input signal, based on adaptive frequency oscillators, and the dynamical system responsible for learning of the waveform with a built in learning algorithm. By combining the two dy...
متن کاملAnalysis of Switching Dynamics with Competing Neural Networks
We present a framework for the unsupervised segmentation of time series. It applies to non-stationary signals originating from di erent dynamical systems which alternate in time, a phenomenon which appears in many natural systems. In our approach, predictors compete for data points of a given time series. We combine competition and evolutionary inertia to a learning rule. Under this learning ru...
متن کامل