There has been much discussion recently about the scope and limits of purely symbolic models of the mind and about the proper role of connectionism in cognitive modeling. This paper describes the symbol grounding problem : How can the semantic interpretation of a formal symbol system be made intrinsic to the system, rather than just parasitic on the meanings in our heads? How can the meanings of the meaningless symbol tokens, manipulated solely on the basis of their shapes, be grounded (...) in anything but other meaningless symbols? The problem is analogous to trying to learn Chinese from a Chinese/Chinese dictionary alone. A candidate solution is sketched: Symbolic representations must be grounded bottom-up in nonsymbolic representations of two kinds: iconic representations, which are analogs of the proximal sensory projections of distal objects and events, and categorical representations, which are learned and innate feature-detectors that pick out the invariant features of object and event categories from their sensory projections. Elementary symbols are the names of these object and event categories, assigned on the basis of their categorical representations. Higher-order symbolic representations, grounded in these elementary symbols, consist of symbol strings describing category membership relations. Connectionism is one natural candidate for the mechanism that learns the invariant features underlying categorical representations, thereby connecting names to the proximal projections of the distal objects they stand for. In this way connectionism can be seen as a complementary component in a hybrid nonsymbolic/symbolic model of the mind, rather than a rival to purely symbolic modeling. Such a hybrid model would not have an autonomous symbolic module, however; the symbolic functions would emerge as an intrinsically dedicated symbol system as a consequence of the bottom-up grounding of categories ' names in their sensory representations. Symbol manipulation would be governed not just by the arbitrary shapes of the symbol tokens, but by the nonarbitrary shapes of the icons and category invariants in which they are grounded. (shrink)

On the occasion of a first conference on Cognitive Science, it seems appropriate to review the basis of common understanding between the various disciplines. In my estimate, the most fundamental contribution so far of artificial intelligence and computer science to the joint enterprise of cognitive science has been the notion of a physical symbol system, i.e., the concept of a broad class of systems capable of having and manipulating symbols, yet realizable in the physical universe. The notion of symbol so (...) defined is internal to this concept, so it becomes a hypothesis that this notion of symbols includes the symbols that we humans use every day of our lives. In this paper we attempt systematically, but plainly, to lay out the nature of physical symbol systems. Such a review is in ways familiar, but not thereby useless. Restatement of fundamentals is an important exercise. (shrink)

Replication or even modelling of consciousness in machines requires some clarifications and refinements of our concept of consciousness. Design of, construction of, and interaction with artificial systems can itself assist in this conceptual development. We start with the tentative hypothesis that although the word “consciousness” has no well-defined meaning, it is used to refer to aspects of human and animal informationprocessing. We then argue that we can enhance our understanding of what these aspects might be by designing and building virtual-machine (...) architectures capturing various features of consciousness. This activity may in turn nurture the development of our concepts of consciousness, showing how an analysis based on information-processing virtual machines answers old philosophical puzzles as well enriching empirical theories. This process of developing and testing ideas by developing and testing designs leads to gradual refinement of many of our pre-theoretical concepts of mind, showing how they can be construed as implicitly “architecture-based” concepts. Understanding how humanlike robots with appropriate architectures are likely to feel puzzled about qualia may help us resolve those puzzles. The concept of “qualia” turns out to be an “architecture-based” concept, while individual qualia concepts are “architecture-driven”. (shrink)

Received by the IRE, October 24, 1960. The author's work summarized here—which was done at the MIT Lincoln Laboratory, a center for research operated by MIT at Lexington, Mass., with the joint Support of the U. S. Army, Navy, and Air Force under Air Force Contract AF 19-5200; and at the Res. Lab. of Electronics, MIT, Cambridge, Mass., which is supported in part by the U. S. Army Signal Corps, the Air Force Office of Scientific Research, and the ONR—is based (...) on earlier work done by the author as a Junior Fellow of the Society of Fellows, Harvard University. (shrink)

When your word processor or email program is running on your computer, this creates a "virtual machine” that manipulates windows, files, text, etc. What is this virtual machine, and what are the virtual objects it manipulates? Many standard arguments in the philosophy of mind have exact analogues for virtual machines and virtual objects, but we do not want to draw the wild metaphysical conclusions that have sometimes tempted philosophers in the philosophy of mind. A computer file is not made of (...) epiphenomenal ectoplasm. I argue instead that virtual objects are "supervenient objects". The stereotypical example of supervenient objects is the statue and the lump of clay. To this end I propose a theory of supervenient objects. Then I turn to persons and mental states. I argue that my mental states are virtual states of a cognitive virtual machine implemented on my body, and a person is a supervenient object supervening on his cognitive virtual machine. (shrink)

Theorems in automated theorem proving are usually proved by formal logical proofs. However, there is a subset of problems which humans can prove by the use of geometric operations on diagrams, so called diagrammatic proofs. Insight is often more clearly perceived in these proofs than in the corresponding algebraic proofs; they capture an intuitive notion of truthfulness that humans find easy to see and understand. We are investigating and automating such diagrammatic reasoning about mathematical theorems. Concrete, rather than general diagrams (...) are used to prove particular concrete instances of the universally quantified theorem. The diagrammatic proof is captured by the use of geometric operations on the diagram. These operations are the inference steps of the proof. An abstracted schematic proof of the universally quantified theorem is induced from these proof instances. The constructive -rule provides the mathematical basis for this step from schematic proofs to theoremhood. In this way we avoid the difficulty of treating a general case in a diagram. One method of confirming that the abstraction of the schematic proof from the proof instances is sound is proving the correctness of schematic proofs in the meta-theory of diagrams. These ideas have been implemented in the system, called Diamond, which is presented here. (shrink)

This is not a scholarly research paper, but a ‘position paper’ outlining an approach to the study of mind which has been gradually evolving since about 1969 when I first become acquainted with work in Artificial Intelligence through Max Clowes. I shall try to show why it is more fruitful to construe the mind as a control system than as a computational system.

"The Emperor's New Mind" by Roger Penrose has received a great deal of both praise and criticism. This review discusses philosophical aspects of the book that form an attack on the "strong" AI thesis. Eight different versions of this thesis are distinguished, and sources of ambiguity diagnosed, including different requirements for relationships between program and behaviour. Excessively strong versions attacked by Penrose (and Searle) are not worth defending or attacking, whereas weaker versions remain problematic. Penrose (like Searle) regards the notion (...) of an algorithm as central to AI, whereas it is argued here that for the purpose of explaining mental capabilities the architecture of an intelligent system is more important than the concept of an algorithm, using the premise that what makes something intelligent is not what it does but how it does it. What needs to be explained is also unclear: Penrose thinks we all know what consciousness is and claims that the ability to judge Go "del's formula to be true depends on it. He also suggests that quantum phenomena underly consciousness. This is rebutted by arguing that our existing concept of "consciousness" is too vague and muddled to be of use in science. This and related concepts will gradually be replaced by a more powerful theory-based taxonomy of types of mental states and processes. The central argument offered by Penrose against the strong AI thesis depends on a tempting but unjustified interpretation of Goedel's incompleteness theorem. Some critics are shown to have missed the point of his argument. A stronger criticism is mounted, and the relevance of mathematical Platonism analysed. Architectural requirements for intelligence are discussed and differences between serial and parallel implementations analysed. (shrink)

he design-based approach is a methodology for investigating mechanisms capable of generating mental phenomena, whether introspectively or externally observed, and whether they occur in humans, other animals or robots. The study of designs satisfying requirements for autonomous agency can provide new deep theoretical insights at the information processing level of description of mental mechanisms. Designs for working systems (whether on paper or implemented on computers) can systematically explicate old explanatory concepts and generate new concepts that allow new and richer interpretations (...) of human phenomena. To illustrate this, some aspects of human grief are analysed in terms of a particular information processing architecture being explored in our research group. We do not claim that this architecture is part of the causal structure of the human mind; rather, it represents an early stage in the iterative search for a deeper and more general architecture, capable of explaining more phenomena. However even the current early design provides an interpretative ground for some familiar phenomena, including characteristic features of certain emotional episodes, particularly the phenomenon of perturbance (a partial or total loss of control of attention). The paper attempts to expound and illustrate the design-based approach to cognitive science and philosophy, to demonstrate the potential effectiveness of the approach in generating interpretative possibilities, and to provide first steps towards an information processing account of `perturbant', emotional episodes. (shrink)

This is a philosophical `position paper' (html and pdf versions), starting from the observation that we have an intuitive grasp of a family of related concepts of ``possibility'', ``causation'' and ``constraint'' which we often use in thinking about complex mechanisms, and perhaps also in perceptual processes, which according to Gibson are primarily concerned with detecting positive and negative affordances, such as support, obstruction, graspability, etc. We are able to talk about, think about, and perceive possibilities, such as possible shapes, possible (...) pressures, possible motions, and also risks, opportunities and dangers. We can also think about constraints linking such possibilities. If such abilities are useful to us (and perhaps other animals) they may be equally useful to intelligent artefacts. All this bears on a collection of different more technical topics, including modal logic, constraint analysis, qualitative reasoning, naive physics, the analysis of functionality, and the modelling design processes. The paper suggests that our ability to use knowledge about ``de-re'' modality is more primitive than the ability to use ``de-dicto'' modalities, in which modal operators are applied to sentences. The paper explores these ideas, links them to notions of ``causation'' and ``machine'', suggests that they are applicable to virtual or abstract machines as well as physical machines. Some conclusions are drawn regarding the nature of mind and consciousness. (shrink)