Emotion as an integrative process between non-symbolic and
symbolic systems in intelligent agents
Abstract
This paper briefly considers the story so far in AI on agent control architectures and the later equivalent debate between symbolic and situated cognition in cognitive science. It argues against the adoption of a reductionist position on symbolically-represented cognition but in favour of an ac- count consistent with embodiment. Emotion is put forward as a possible integrative mechanism via its role in the management of interaction between processes and a number of views of emotion are considered. A sketch of how this interaction might be modelled is discussed.
This heretical article suggests that while embodiment was key to evolving human culture, and clearly affects our thinking and word choice now (as do many things in our environment), our culture may have evolved to such a point that a purely memetic AI beast could pass the Turing test. Though making something just like a human would clearly require both embodiment and memetics, if we were forced to choose one or the other, memetics might actually be easier. This short paper argues this point, and discusses what it would take to move beyond current semantic priming results to a human-like agent.
This paper discusses our views on the future of the field of cognitive architectures, and how the scien- tific questions that define it should be addressed. We also report on a set of requirements, and a related architecture design, that we are currently investigating as part of the CoSy project.
Given the limitations of human researchers' minds, it is necessary to decompose systems and then address the problem of how to integrate at some level of abstraction. Connectionism and numerical methods need to be combined with symbolic processing, with the emphasis on scaling to large numbers of competencies and knowledge sources and to large state spaces. A proposal is briefly outlined that uses overlapping oscillations in a 3-D grid to address disparate problems. Two selected problems are the use of analogy in commercial software evolution and the analysis of medical im- ages.
The focus of any attempt to create an artificial brain and mind should reside in the dynamic model of the network of information. The study of biological networks has progressed enormously in recent years. It is an intriguing possibility that the architecture of representation and exchange of information at high level closely resembles that of neurons. Taking this hypothesis into account, we designed an experiment, concerning the way ideas are organised according to human perception. The experiment is divided into two parts: a visual task and a verbal task. A network of ideas was constructed using the results of the experiment. Statistical analysis showed that the verbally invoked network has the same topological structure as the visually invoked one, but the two networks are distinct.
Social learning is an important source of human knowledge, and the degree to which we do it sets us apart from other animals. In this short paper, I examine the role of social learning as part of a complete agent, identify what makes it possible and what additional functionality is needed. I do this with reference to COIL, a working model of imitation learning.
Updated: 13 Mar 2006
Aaron Sloman