Our work addresses the problem of autonomous concept formation from a design point of view, providing an initial answer to the question: What are the design features of an architecture supporting the acquisition of different types of concepts by an autonomous agent?Autonomous agents, that is systems capable of interacting independently with their environment in the pursuit of their own goals, will provide the framework in which we study the problem of autonomous concept formation. Humans and most animals may in this sense also be regarded as autonomous agents, but our concern will be with artificial autonomous agents. A detailed survey and discussion of the many issues surrounding the notion of `artificial agency' is beyond the scope of this thesis and a good overview can be found in [Wooldridge and Jennings, 1995]. Instead we will focus on how artificial agents could be endowed with representational and modelling capabilities.
The ability to form concepts is an important and recognised cognitive ability, thought to play an essential role in related abilities such as categorisation, language understanding, object identification and recognition, reasoning, all of which can be seen as different aspects of intelligence. Concepts and categories are studied within cognitive science, where scientists are concerned with human conceptual abilities and mental representations of categories, but they have been addressed also in the rather different domain of machine learning and classificatory data analysis, where the focus is on the development of algorithms for clustering problems and induction problems [Mechelen et al., 1993]. The two fields are well distinct and only recently have started to interact, but even though the importance of concepts has been recognised, the nature of concepts is controversial, in the sense that there is no commonly agreed theory of concepts, and it is still far from obvious which representational means are most suited to capture the many cognitive functions that concepts are involved in.
Among the goals of this thesis there is the attempt to bring together different lines of argumentation that have emerged within philosophy, cognitive science and AI, in order to establish a solid foundation for further research into the representation and acquisition of concepts by autonomous agents. Thus, our results and conclusions will often be stated in terms of new insights and ideas, rather than resulting in new algorithms or formal methods.
Our focus will be on affordance concepts -- discussed in detail in Chapter 4 -- and our main contributions will be:
When addressing concept formation in AI, what can be called the `system level' is often overlooked, which means that concepts and categories are rarely studied from the point of view of a system, autonomous and complete, that might need such constructs and can acquire them only by means of interactions with its environment, under the constraints of its cognitive architecture. Also within psychology, the focus is usually on structural aspects of concepts rather than on developmental issues [Smith and Medin, 1981]. Our approach - an architecture-based approach - is an attempt (i) to show that a system level perspective on concept formation is indeed possible and worth exploring, and (ii) to provide an initial, maybe simple, but concrete example of the insights that can be gained from such an approach. Since the methodology that we propose to study concept formation is a general one, and can be applied also to other types of concepts, we decided to mention broadly `autonomous concept formation' rather than `autonomous affordance-concepts formation' in the title of the thesis.
- An argument showing that concepts should be thought of as belonging to different kinds, where the differences among these kinds are to be captured in terms of architecture features supporting their acquisition.
- A description (and partial implementation) of a minimal architecture (the Adaptive Behaviour architecture - AB architecture for short) supporting the acquisition of affordance concepts; the AB architecture is actually a proposal for a sustaining mechanism, in the sense of [Margolis, 1999], for affordances, and makes clear the necessity of a minimal structure for the representation of affordances.
Chapter 1 is an introduction to the problem. We discuss, from a rather philosophical point of view, the notion of `concept' and we illustrate the relevance of concept formation as an AI problem.Chapter 2 reviews the different theories of concepts proposed in the philosophical, psychological and AI literature, in order to give a broad overview of the different positions, the types of questions raised, and the solutions that have been proposed.
In Chapter 3 we discuss our methodology and we give an initial overview of the scenario we used to ground our analyses.
Chapter 4 addresses the question of whether distinct kinds of concepts can be individuated and on which basis. We argue for the superiority of a processing-based distinction and account for taxonomic concepts, goal-derived concepts and affordance concepts as distinct concept kinds.
Chapter 5 presents the AB-architecture, a minimal architecture for the acquisition of affordance concepts.
Finally Chapter 6 discusses the contributions of our work, its limitations and the possibilities for future research.
Part of the
Cognition and Affect Project
Maintained by
Aaron Sloman
Updated: 9 Aug 2007