Within a statistical learning setting, we propose and study an iterative regularization algorithm for least squares defined by an incremental gradient method. In particular, we show that, if all other parameters are fixed a priori, the number of passes over the data (epochs) acts as a regularization parameter, and prove strong universal consistency, i.e. almost sure convergence of the risk, as ...

The present study aims at insights into the nature of incremental learning in the context of Gold’s model of identification in the limit. With a focus on natural requirements such as consistency and conservativeness, incremental learning is analysed both for learning from positive examples and for learning from positive and negative examples. The results obtained illustrate in which way differe...

This paper addresses the problem of automated derivation of non-zeno behaviour models from goal models. The approach uses a novel combination of model checking and machine learning. We first translate a goal model formalised in linear temporal logic into a (potentially zeno) labelled transition system. We then iteratively identify zeno traces in the model and learn operational requirements in t...

Monotonic convergence of iterative learning control systems with variable pass length Thomas Seel, Thomas Schauer & Jörg Raisch To cite this article: Thomas Seel, Thomas Schauer & Jörg Raisch (2017) Monotonic convergence of iterative learning control systems with variable pass length, International Journal of Control, 90:3, 393-406, DOI: 10.1080/00207179.2016.1183172 To link to this article: ht...

i i i i i i Cover illustration: ILC applied to a problem where, for example, a robot tool is supposed to track a circular path. In the beginning, the tracking performance is poor, but as the ILC algorithm " learns " , the performance improves and comes very close to a perfect circle. The orange colour represents the connection to the experiments performed on ABB robots. Linköping studies in sci...

The paper analyzes the flow calculation of power system, using iterative learning algorithm to calculation the power flow, compare with traditional improving Newton etc. algorithm, Iterative learning algorithm has fast convergence can also be to achieve a high precision tracking. In this paper convergence of the algorithm is global, and gives control of the convergence conditions and rigorous t...

System parameter identification is a necessary prerequisite for model-based control. In this paper, we propose an approach to estimate model parameters of robot servo actuators that does not require special testing equipment. We use Iterative Learning Control to determine the motor commands needed to follow a reference trajectory. To identify parameters, we fit a model for DC motors and frictio...

This paper focuses on the identification problem ofWiener nonlinear systems.The application of the key-term separation principle provides a simplified form of the estimated parameter model. To solve the identification problem of Wiener nonlinear systems with the unmeasurable variables in the information vector, the least-squares-based iterative algorithm is presented by replacing the unmeasurab...

This paper assesses the learning capabilities of agents in a situation of collective choice. Each agent is endowed with a private preference concerning a number of alternative candidates, and participates in an iterated plurality election. Agents get rewards depending on the winner of each election, and adjust their voting strategy using reinforcement learning. By conducting extensive simulatio...