Machine consciousness.

A review of work from several laboratories on modeling consciousness, ranging from functional models that prioritize behavior to material models grounded in brain anatomy. Functional approaches include applications for job-finding where a machine must be indistinguishable from a conscious human, using global workspace theories. Material approaches model attentional brain mechanisms and biochemical processes in children. The chapter distinguishes between attempts to model phenomenology (synthetic phenomenology) and those that do not. Studying consciousness through machine design is expected to produce a computational language for expressing consciousness and computational methods for building flexible, competent machinery.

Study at a glance

Abstract

The work from several laboratories on the modeling of consciousness is reviewed. This ranges, on one hand, from purely functional models where behavior is important and leads to an attribution of consciousness to, on the other hand, material work closely derived from the information about the anatomy of the brain. At the functional end of the spectrum, applications are described specifically directed at a job-finding problem, where the person being served should not discern between being served by a conscious human or a machine. This employs an implementation of global workspace theories. At the material end, attempts at modeling attentional brain mechanisms, and basic biochemical processes in children are discussed. There are also general prescriptions for functional schemas that facilitate discussions for the presence of consciousness in computational systems and axiomatic structures that define necessary architectural features without which it would be difficult to represent sensations. Another distinction between these two approaches is whether one attempts to model phenomenology (material end) or not (functional end). The former is sometimes called "synthetic phenomenology." The upshot of this chapter is that studying consciousness through the design of machines is likely to have two major outcomes. The first is to provide a wide-ranging computational language to express the concept of consciousness. The second is to suggest a wide-ranging set of computational methods for building competent machinery that benefits from the flexibility of conscious representations.