Abstract
The aim of behavioural cloning is to synthesize artificial controllers that are robust and comprehensible to human understanding. To attain the two objectives we propose the use of the Incremental Correction model that is based on a closed-loop control strategy to model the reactive aspects of human control skills. We have investigated the use of three different representations to encode the artificial controllers: univariate decision trees as induced by C4.5; multivariate decision and regression trees as induced by cart and; clausal theories induced by an Inductive Logic Programming (ILP) system. We obtained an increase in robustness and a lower complexity of the controllers when compared with results using other models. The controllers synthesized by cart revealed to be the most robust. The ILP system produced the simpler encodings. © Springer-Verlag Berlin Heidelberg 2001.

Abstract

Abstract
There is a growing interest in understanding consumer ethical actions in relation to their dealings with firms. This paper examines whether there are differences between Northern and Southern European Union (EU) consumers' perceptions of ethical consumer behaviour using Muncy and Vitell's (1992) Consumer Ethics Scale (CES). The study samples 962 university students across four Northern EU countries (Germany, Denmark, Scotland, The Netherlands) and four Southern EU countries (Portugal, Spain, Italy, Greece). Some differences are identified between the two samples, which might question the ability of organisations to consider the EU as one homogeneous market.

Abstract
We propose a model, called Incremental Correction. (IC) model to address the problem of reverse engineering human control skills using the Behavioural Cloning methodology. The proposed model is based on the concept of closed loop or feedback control. The controllers are induced via Machine Learning tools from traces of human expert control performance. Controllers using the IC model exhibit an increase in robustness and a reduction in encoding complexity when compared to previous models used in behavioural cloning.

Abstract
For uniformly asymptotically affine (uaa) Markov maps on train tracks, we prove the following type of rigidity result: if a topological conjugacy between them is (uaa) at a point in the train track then the conjugacy is (uaa) everywhere. In particular, our methods apply to the case in which the domains of the Markov maps are Canter sets. We also present similar statements for (uaa:) and C-r Markov families. These results generalize the similar ones of Sullivan and de Faria for C-r expanding circle maps with r > 1 and have useful applications to hyperbolic dynamics on surfaces and laminations.

Abstract
We give an elementary proof of existence and uniqueness of Gibbs states for Holder weight systems on subshifts of finite type. This uses a notion of duality for such subshifts. The approach of Paterson [2] is used to construct a measure with a prescribed Jacobian and the duality is used to produce an invariant measure from this.