Learning and exploiting context in agents

Modélisation et utilisation du contexte

Les recherches de ces 50 dernières années ont montré que le raisonnement avec et à propos du contexte est un aspect essentiel de la cognition humaine, imprégnant le langage, la mémoire et les capacités de raisonnement. L'ensemble de ce processus est développé au cours du temps par un apprentissage basé sur l'expérience. En supposant que le but de l'intelligence artificielle est de doté une machine d'une intelligence proche de celle des humains, il est essentiel de considérer et incorporer le concept de contexte dans la conception et l'implémentation des systèmes intelligents. Ce papier discute du raisonnement contextuel chez l'humain et comment celui-ci aide les humains à faire face avec succès à des tâches cognitives complexes. Nous relions de plus cette recherche sur le contexte en psychologie cognitive aux recherches actuelles sur le raisonnement contextuel ans les systèmes d'intelligence artificielle. ABSTRACT. Research over the last 50 years has shown that reasoning with and about context is an essential aspect of human cognition, permeating language, memory, and reasoning capabilities. This integral process is developed over a lifetime through experiential learning. Given the goal of artificial intelligence to create human-like intelligence in a machine, it is essential to consider and incorporate the concept of context in intelligent system design and implementation. This paper discusses contextual reasoning in humans and how it helps humans successfully deal with complex cognitive tasks. We further link this research on context in cognitive psychology with the current research in contextual reasoning in Artificial Intelligence systems. MOTS-CLÉS. Contexte dans la cognition humaine, raisonnement contextuel, Contexte dans la cognition humaine, raisonnement contextuel. KEYWORDS. Context in human cognition, contextual reasoning, role of context in learning.

Journal of Experimental and Theoretical Artificial Intelligence, 2000

In this paper we provide a foundation of a theory of contextual reasoning from the perspective of a theory of knowledge representation. Starting from the so-called metaphor of the box, we £rstly show that the mechanisms of contextual reasoning proposed in the literature can be classi£ed into three general forms (called localised reasoning, push and pop, and shifting). Secondly, we provide a justi£cation of this classi£cation, by showing that each mechanism corresponds to operating on a fundamental dimension along which context dependent representations may vary (namely, partiality, approximation, and perspective). From the previous analysis, we distill two general principles of a logic of contextual reasoning. Finally, we show that these two principles can be adequately formalised in the framework of MultiContext Systems. In the last part of the paper, we provide a practical illustration of the ideas discussed in the paper by formalising a simple scenario, called the Magic Box problem.

2007

Both learning and reasoning are important aspects of intelligence. However they are rarely integrated within a single agent. Here it is suggested that imprecise learning and crisp reasoning may be coherently combined via the cognitive context. The identification of the current context is done using an imprecise learning mechanism, whilst the contents of a context are crisp models that may be usefully reasoned about.

International Conference on Agents and Artificial Intelligence, 2009

Knowledge and Information Systems - KAIS

Ambient Intelligence environments host various agents that collect, process, change and share the available context information. The imperfect nature of context, the open and dynamic nature of such environments and the special characteristics of ambient agents have introduced new research challenges in the study of Distributed Artiflcial Intelligence. This paper proposes a solution based on the Multi-Context Sys- tems paradigm, according to which local knowledge of ambient agents is encoded in rule theories (contexts), and information ∞ow between agents is achieved through mapping rules that associate concepts used by difierent contexts. To resolve potential inconsis- tencies that may arise from the interaction of contexts through their mappings (global con∞icts), we use a preference ordering on the system contexts, which may express the confldence that an agent has in the knowledge imported by other agents. On top of this model, we have developed four alternative strategies for glo...

2002

In the area of agent-based computing there are many proposals for specific system architectures, and a number of proposals for general approaches to building agents. As yet, however, there are comparatively few attempts to relate these together, and even fewer attempts to provide methodologies which relate designs to architectures and then to executable agents.

2002

Sharing ontology, sensing context and reasoning are crucial to the realization of context-aware software agents. This document describes our effort on using Resource Description Framework (RDF) and the Prolog Forward Chaining (P fc ) system to provide support for ontology sharing and reasoning in the CoolAgent Recommendation System (CoolAgent RS), a context-aware multi-agent system. This document also describes the implementation of the CoolAgent RS document and cuisine recommendation services that provide tailored services by exploiting user’s context.

The Florida AI Research Society Conference, 2004

This paper is an extension to and revision of Gonzalez and Ahlers' (6) definition of the Context-Based Reasoning Paradigm. Included are rigorous definitions of all terms and components applicable to CxBR models along with a discussion on how and where these models store and execute tactical knowledge. In addition, new terms and concepts are introduced that justify the need for

The first International and Interdisciplinary Conference on Modeling and Using Context (CONTEXT-97) held at Rio de Janeiro, Brazil on February 4-6, 1997. This article provides a summary of the presentations and discussions during the three days with a focus on context in applications. The notion of context is far from defined and is dependent in its interpretation on a cognitive science versus an engineering (or system building) point of view. However, the conference make it possible to identify new trends in the formalization of context at a theoretical level as well as in the use of context in real-world applications. Results presented at the conference are ascribed in the realm of the works on context over the past few years at specific workshops and symposia. The diversity of the attendees' origins (Artificial Intelligence, Linguistics, Philosophy, Psychology, etc.) demonstrates that there are different types of context, not a unique one. For instance, logicians model context at the level of the knowledge representation and the reasoning mechanisms while cognitive scientists consider context at the level of the interaction between two agents (i.e., two humans or a human and a machine). In the later case, there are now strong arguments proving that one can speak of context only in reference to its use (e.g., context of an item or of a problem solving exercise). Moreover, there are different types of context that are interdependent. This makes it possible to understand why despite the consensus on some context aspects, agreement on the notion of context is not yet achieved.

Applied Ontology, 2019

This paper describes the layers of context leveraged by language-endowed intelligent agents (LEIAs) during incremental natural language understanding (NLU). Context is defined as a combination of (a) the perceptual stimuli available to the agent at the given point in time, and (b) the knowledge elements and reasoning activated at the given stage of the agent's interpretation of those stimuli. This approach to NLU addresses the treatment of a large number of difficult linguistic phenomena that are essential for high-quality NLU but are not being tackled by the knowledge-lean approaches that are typical of modernday natural language processing. Although LEIAs are being developed as components of prototype application systems, this paper is not about implementations or evaluations-its contribution is conceptual, with everything described applicable to any artificial intelligent agent environment.