Contents

REFEREED ARTICLES

Owen Holland
Editorial Introduction   full text
Igor Aleksander & Barry Dunmall
Axioms and Tests for the Presence of Minimal Consciousness in Agents abstract
Susan Blackmore
Consciousness in Meme Machines  abstract
Rodney M.J. Cotterill
CyberChild: A Simulation Test-Bed for Consciousness Studies  abstract
Stan Franklin
IDA: A Conscious Artifact?  abstract
Stevan Harnad
Can a Machine Be Conscious? How?  abstract
Owen Holland & Rod Goodman
Robots With Internal Models: A Route to Machine Consciousness?  abstract
Jesse J. Prinz
Level-Headed Mysterianism and Artificial Experience  abstract
Aaron Sloman & Ron Chrisley
Virtual Machines and Consciousness  abstract
Luc Steels
Language Re-Entrance and the ‘Inner Voice’  abstract
William Irwin Thompson
The Borg or Borges?  full text

ABSTRACTS

Igor Aleksander and Barry Dunmall

Axioms and Tests for the Presence of Minimal Consciousness in Agents

This paper relates to a formal statement of the mechanisms that are thought minimally necessary to underpin consciousness. This is expressed in the form of axioms. We deem this to be useful if there is ever to be clarity in answering questions about whether this or the other organism is or is not conscious. As usual, axioms are ways of making formal statements of intuitive beliefs and looking, again formally, at the consequences of such beliefs. The use of this style of exposition does not entail a claim to provide a mathematically rigorous formal deductive system. Conventional mathematical notation is used to achieve clarity, although this is elaborated with natural language in an attempt to reduce terseness. In our view, making the approach axiomatic is synonymous with building clear usable tests for consciousness and is therefore a central feature of the paper.

The extended scope of this approach is to lay down some essential properties that should be considered when designing machines that could be said to be conscious. In the broader discussion about the nature of consciousness and its neurological mechanisms, it may seem to some that axiomatisation is premature and continues to beg many questions. However, the approach is meant to be open- ended so that others can build further axiomatic clarifications that address the very large number of questions which, in the search for a formal basis for consciousness, still remain to be answered. Of course, in discussions about consciousness many will also argue that the subject is not one that may ever be formally addressed by means of axioms. The view taken in this paper is ‘let’s try to do it and see how far it gets’.

Correspondence: Igor Aleksander and Barry Dunmall, Intelligent and Interactive Systems Group, Department of Electrical and Electronic Engineering, Imperial College, London SW7 2BT, U.K.

Susan Blackmore

Consciousness in Meme Machines

Setting aside the problems of recognising consciousness in a machine, this article considers what would be needed for a machine to have human-like consciousness. Human-like consciousness is an illusion; that is, it exists but is not what it appears to be. The illusion that we are a conscious self having a stream of experiences is constructed when memes compete for replication by human hosts. Some memes survive by being promoted as personal beliefs, desires, opinions and possessions, leading to the formation of a memeplex (or selfplex). Any machine capable of imitation would acquire this type of illusion and think it was conscious. Robots that imitated humans would acquire an illusion of self and consciousness just as we do. Robots that imitated each other would develop their own separate languages, cultures and illusions of self. Distributed seflplexes in large networks of machines are also possible. Unanswered questions include what remains of consciousness without memes, and whether artificial meme machines can ever transcend the illusion of self consciousness.

Rodney M.J. Cotterill

CyberChild: A Simulation Test-Bed for Consciousness Studies

Abstract: The first brief description is given of a project aimed at searching for the neural correlates of consciousness through computer simulation. The underlying model is based on the known circuitry of the mammalian nervous system, the neuronal groups of which are approximated as binary composite units. The simulated nervous system includes just two senses — hearing and touch — and it drives a set of muscles that serve vocalisation, feeding and bladder control. These functions were chosen because of their relevance to the earliest stages of human life, and the simulation has been given the name CyberChild. The system’s pain receptors respond to a sufficiently low milk level in the stomach, if there is simultaneously a low level of blood sugar, and also to a full bladder and an unchanged diaper. It is believed that it may be possible to infer the presence of consciousness in the simulation through observations of CyberChild’s behaviour, and from the monitoring of its ability to ontogenetically acquire novel reflexes. The author has suggested that this ability is the crucial evolutionary advantage of possessing consciousness. The project is still in its very early stages, and although no suggestion of consciousness has yet emerged, there appears to be no fundamental reason why consciousness could not ultimately develop and be observed.

Correspondence: Rodney Cotterill, Biophysics, Building 307, Danish Technical University, 2800 Lyngby, Denmark. Email: rodney.cotterill@fysik.dtu.dk

Stan Franklin

IDA: A Conscious Artifact?

Abstract: After discussing various types of consciousness, several approaches to machine consciousness, software agent, and global workspace theory, we describe a software agent, IDA, that is ‘conscious’ in the sense of implementing that theory of consciousness. IDA perceives, remembers, deliberates, negotiates, and selects actions, sometimes ‘consciously’. She uses a variety of mechanisms, each of which is briefly described. It’s tempting to think of her as a conscious artifact. Is such a view in any way justified? The remainder of the paper considers this question.

Correspondence: Stan Franklin, Institute for Intelligent Systems, The University of Memphis, Memphis, TN 38152, USA. Email: franklin@memphis.edu

Stevan Harnad

Can a Machine Be Conscious? How?

Asking whether a machine can be conscious is rather like asking whether one has stopped beating one’s wife: The question is so heavy with assumptions that either answer would be incriminating! The answer, of course, is: It depends entirely on what you mean by ‘machine’! If you mean the current generation of man-made devices (toasters, ovens, cars, computers, today’s robots), the answer is: almost certainly not.

Correspondence:  Stevan Harnad, Centre de Neuroscience de la Cognition (CNC), Université du Québec à Montréal, CP 8888 Succursale Centre-Ville, Montréal, Québec, Canada H3C 3P8. Email: harnad@uqam.ca

Owen Holland and Rod Goodman

Robots With Internal Models: A Route to Machine Consciousness?

The starting point we have chosen is at the conjunction of four fairly uncontroversial observations:
  • consciousness is known to arise from the operation of the human brain
  • of all brains, the human brain has the highest capacity for intelligence
  • the human brain evolved from simpler brains
  • the human brain is a control system
    • Taken together, these suggest a strategy: step by step, develop a series of control systems capable of demonstrating increasingly high intelligence, and monitor their performance at each stage to see when and if they show any signs of consciousness. The immediate appeal is that it does not involve sitting down and ‘inventing’ machine consciousness, or human-level intelligence, either of which would be extremely problematical; the technical aspect of this approach involves nothing more than the successive development of a series of control systems for producing increasingly intelligent behaviour, and that is a reasonable goal for engineers. Of course, it may also be completely misguided, in that high intelligence may not automatically entail consciousness, but, given the present state of ignorance about so much to do with consciousness, it seems a risk worth taking.

    This paper explores some of the issues relevant to the consciousness-via- incremental-intelligence programme, and makes two key design decisions: to embody intelligence in a physical robot, and to concentrate on the exploitation of internal models. It also presents some speculations about how the pursuit of intelligence in this way may lead us to a system with at least some of the characteristics of consciousness.

    Correspondence: Owen Holland, Department of Computer Science, University of Essex, Wivenhoe Park CO4 3SQ, UK. Email: owen@essex.ac.uk

    Jesse J. Prinz

    Level-Headed Mysterianism and Artificial Experience

    Many materialists believe that we should, in principle, be able to build a conscious computing machine. Others disagree. I favour a sceptical position, but of another variety. The problem isn’t that it would be impossible to create a conscious computer. The problem is that we cannot know whether it is possible. There are principled reasons for thinking that we wouldn’t ever be able to confirm that allegedly conscious computers were conscious. The proper stance on computational consciousness is agnosticism. Despite this agnosticism, I think we are very close to understanding the material basis of consciousness. Close, but we will never get all the way there. Our understanding of the material basis of consciousness is ineluctably incomplete. That makes me a mysterian. But I am not a defeatist mysterian. I do not think the irresolvable mysteries of consciousness prevent us from formulating concrete empirically grounded theories of consciousness. I will even outline such a theory below

    Correspondence: Jesse Prinz, Department of Philosophy, Caldwell Hall, University of North Carolina, Chapel Hill, NC 27599, USA. Email: jesse@subcortex.com

    Aaron Sloman and Ron Chrisley

    Virtual Machines and Consciousness

    Abstract: 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 information processing. 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 human-like 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’.

    Correspondence:
    School of Computer Science, The University of Birmingham, Birmingham B15 2TT, U.K.
    Email: A.Sloman@cs.bham.ac.uk  R.L.Chrisley@cs.bham.ac.uk

    Luc Steels

    Language Re-Entrance and the ‘Inner Voice’

    Abstract: As soon as we stop talking aloud, we seem to experience a kind of ‘inner voice’, a steady stream of verbal fragments expressing ongoing thoughts. What kind of information processing structures are required to explain such a phenomenon? Why would an ‘inner voice’ be useful? How could it have arisen? This paper explores these questions and reports briefly some computational experiments to help elucidate them.

    Correspondence: Luc Steels, Free University of Brussels, VUB AI Laboratory, 10G-725,  Pleinlaan 2, B-1050 Brussels, Belgium. Email: steels@arti.vub.ac.be

  • Imprint Academic Home Page
  • JCS Home Page