Connectionist Synthetic Epistemology: Requirements for the Development of Objectivity

A connectionist system that is capable of learning about the spatial structure of a simple world is used for the purposes of synthetic epistemology: the creation and analysis of artificial systems in order to clarify philosophical issues that arise in the explanation of how agents, both natural and artificial, represent the world. In this case, the issues to be clarified focus on the content of representational states that exist prior to a fully objective understanding of a spatial domain. In particular, the criticisms of (Chrisley, 1993) that were raised in (Holland, 1994) are addressed: how can we determine that a system’s spatial representations are more objective than before? And under what conditions (tasks, training regimes, environments) do such increases in objectivity occur? After analysing the results of experiments that attempt to shed light on these questions, the study concludes by comparing and contrasting this work with related research. 1 Synthetic epistemology: Philosophy and AI/ALife Sometimes in order to clarify the theories and concepts one would like to use to explain a natural system, it can be of great assistance to try them out on a simple, artificial system, which allows greater control and clearer analysis. Just as one might more readily come to a clear understanding of the principles of aerodynamics by studying a simple, artificial glider than by studying the particularities of the feathers and muscles of sparrows, so one might also see more readily the general structure of a proper psychology of real systems by first attempting to apply it to a simple, artificial agent. Thus, to clarify some new ideas being proposed for the explanation of natural intentional systems, it seems a promising idea to turn to synthetic epistemology: the creation and analysis of artificial systems in order to clarify philosophical issues that arise in the explanation of how agents, both natural and artificial, represent the world. Synthesis can thus be justified as an approach to understanding epistemology in the same way that it can be justified as an approach to understanding intelligence (AI), or biology (ALife): Artificial systems which exhibit lifelike behaviors are worthy of inves-