ORCID Profile
0000-0003-1614-6808
Current Organisation
FernUniversität in Hagen
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Centro Latino Americano de Estudios en Informatica
Date: 14-04-2021
Abstract: Dealing with dynamics is a vital problem in Artificial Intelligence (AI). An intelligent system should be able to perceive and interact with its environment to perform its tasks satisfactorily. To do so, it must sense external actions that might interfere with its tasks, demanding the agent to self-adapt to the environment dynamics. In AI, the field that studies how a rational agent should change its knowledge in order to respond to a new piece of information is known as Belief Change. It assumes that an agent’s knowledge is specified in an underlying logic that satisfies some properties including compactness: if an information is entailed by a set X of formulae, then this information should also be entailed by a finite subset of X. Several logics with applications in AI, however, do not respect this property. This is the case of many temporal logics such as LTL and CTL. Extending Belief Change to these logics would provide ways to devise self-adaptive intelligent systems that could respond to change in real time. This is a big challenge in AI areas such as planning, and reasoning with sensing actions. Extending belief change beyond the classical spectrum has been shown to be a tough challenge, and existing approaches usually put some constraints upon the system, which are either too restrictive or dispense some of the so desired rational behaviour an intelligent system should present. This is a summary of the thesis “Belief Change without Compactness” by Jandson S Ribeiro. The thesis extends Belief Change to accommodate non-compact logics, keeping the rationality criteria and without imposing extra constraints. We provide complete new semantic perspectives for Belief Change by extending to non-compact logics its three main pillars: the AGM paradigm, the KM paradigm and Non-monotonic Reasoning.
Publisher: American Physical Society (APS)
Date: 25-10-2005
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Date: 17-07-2019
DOI: 10.1609/AAAI.V33I01.33013019
Abstract: Belief change and non-monotonic reasoning are arguably different perspectives on the same phenomenon, namely, jettisoning of currently held beliefs in response to some incompatible evidence. Investigations in this area typically assume, among other things, that the underlying (background) logic is compact, that is, whatever can be inferred from a set of sentences X can be inferred from a finite subset of X. Recent research in the field shows that this compactness assumption can be dispensed without inflicting much damage on the AGM paradigm of belief change. In this paper we investigate the impact of such relaxation on non-monotonic logics instead. In particular, we show that, when compactness is not guaranteed, while the bridge from the AGM paradigm of belief change to expectation logics remains unaffected, the “return trip” from expectation logics to AGM paradigm is no longer guaranteed. We finally explore the conditions under which such guarantee can be given.
Publisher: American Physical Society (APS)
Date: 28-11-2005
Publisher: World Scientific Publishing Company
Date: 02-2006
Publisher: American Physical Society (APS)
Date: 22-11-2005
Publisher: Springer International Publishing
Date: 2015
Publisher: American Physical Society (APS)
Date: 07-03-2006
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: The main paradigms of belief change require the background logic to be Tarskian and finitary. We look at belief update when the underlying logic is not necessarily finitary. We show that in this case the classical construction for KM update does not capture all the rationality postulates for KM belief update. Indeed, this construction, being fully characterised by a subset of the KM update postulates, is weaker. We explore the reason behind this, and subsequently provide an alternative constructive accounts of belief update which is characterised by the full set of KM postulates in this more general framework.
Publisher: Springer International Publishing
Date: 2020
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2022
DOI: 10.24963/KR.2022/30
Abstract: The postulate of relevance provides a suitable and general notion of minimal change for belief contraction. Relevance is tightly connected to smooth kernel contractions when an agent's epistemic state is represented as a logically closed set of formulae. This connection, however, breaks down when an agent's epistemic state is represented as a set of formulae not necessarily logically closed. We investigate the cause behind this schism, and we reconnect relevance with smooth kernel contractions by constraining the behaviour of their choice mechanisms and epistemic preference relations. Our first representation theorem connects smooth kernel contractions with a novel class of epistemic preference relations. For our second representation theorem, we introduce the principle of symmetry of removal that relates relevance to epistemic choices. For the last theorem, we devise a novel class of smooth kernel contractions, that satisfy relevance, which are based on epistemic preference relations that capture the principle of symmetry of removal.
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 09-2021
DOI: 10.24963/KR.2021/50
Abstract: Restoring consistency of a knowledge base, known as consolidation, should preserve as much information as possible of the original knowledge base. On the one hand, the field of belief change captures this principle of minimal change via rationality postulates. On the other hand, within the field of inconsistency measurement, culpability measures have been developed to assess how much a formula participates in making a knowledge base inconsistent. We look at culpability measures as a tool to disclose epistemic preference relations and build rational consolidation functions. We introduce tacit culpability measures that consider semantic counterparts between conflicting formulae, and we define a special class of these culpability measures based on a fixed-point characterisation: the stable tacit culpability measures. We show that the stable tacit culpability measures yield rational consolidation functions and that these are also the only culpability measures that yield rational consolidation functions.
Location: Germany
No related grants have been discovered for Jandson Ribeiro.