Goto

Collaborating Authors

Konev

AAAI Conferences

We study anti-unification for the description logic EL and introduce thenotion of least general generalisation, which generalises simultaneously leastcommon subsumer and concept matching. The idea of generalisation of twoconcepts is to detect maximal similarities between them, and to abstract overtheir differences uniformly. We demonstrate that a finite minimal complete setof generalisations for ELconcepts always exists and establish complexitybounds for computing them. Wepresent an anti-unification algorithm that computes generalisations with afixed skeleton, study its properties and report on preliminary experimental evaluation.


Anti-Unification of Concepts in Description Logic EL

AAAI Conferences

We study anti-unification for the description logic EL and introduce thenotion of least general generalisation, which generalises simultaneously leastcommon subsumer and concept matching. The idea of generalisation of twoconcepts is to detect maximal similarities between them, and to abstract overtheir differences uniformly. We demonstrate that a finite minimal complete setof generalisations for ELconcepts always exists and establish complexitybounds for computing them. Wepresent an anti-unification algorithm that computes generalisations with afixed skeleton, study its properties and report on preliminary experimental evaluation.


Decision Generalisation from Game Logs in No Limit Texas Hold'em

AAAI Conferences

Given a set of data, recorded by observing the decisions of an expert player, we present a case-based framework that allows the successful generalisation of those decisions in the game of no limit Texas Hold'em. We address the problems of determining a suitable action abstraction and the resulting state translation that is required to map real-value bet amounts into a discrete set of abstract actions. We also detail the similarity metrics used in order to identify similar scenarios, without which no generalisation of playing decisions would be possible. We show that we were able to successfully generalise no limit betting decisions from recorded data via our agent, SartreNL, which achieved a 5th place finish out of 11 opponents at the 2012 Annual Computer Poker Competition.


Grossi

AAAI Conferences

The paper develops a formal theory of the degree of justification of arguments, which relies solely on the structure of an argumentation framework. The theory is based on a generalisation of Dung's notion of acceptability, making it sensitive to the numbers of attacks and counter-attacks on arguments. Graded generalisations of argumentation semantics are then obtained and studied. The theory is applied by showing how it can arbitrate between competing preferred extensions and how it captures a specific form of accrual in instantiated argumentation.


Hyperparameters Evidence and Generalisation for an Unrealisable Rule

Neural Information Processing Systems

Using a statistical mechanical formalism we calculate the evidence, generalisation error and consistency measure for a linear perceptron trainedand tested on a set of examples generated by a non linear teacher. The teacher is said to be unrealisable because the student can never model it without error. Our model allows us to interpolate between the known case of a linear teacher, and an unrealisable, nonlinearteacher. A comparison of the hyperparameters which maximise the evidence with those that optimise the performance measuresreveals that, in the nonlinear case, the evidence procedure is a misleading guide to optimising performance. Finally, we explore the extent to which the evidence procedure is unreliable and find that, despite being sub-optimal, in some circumstances it might be a useful method for fixing the hyperparameters. 1 INTRODUCTION The analysis of supervised learning or learning from examples is a major field of research within neural networks.