Aaron Sloman

This paper attempts to characterise a unifying overview of the practice of software engineers, AI designers, developers of evolutionary forms of computation, designers of adaptive systems, etc. The topic overlaps with theoretical biology, developmental psychology and perhaps some aspects of social theory. Just as much of theoretical computer science follows the lead of engineering intuitions and tries to formalise them, there are also some important emerging high level cross disciplinary ideas about natural information processing architectures and evolutionary mechanisms and that can perhaps be unified and formalised in the future. There is some speculation about the evolution of human cognitive architectures and consciousness.

This paper discusses some of the requirements for the control architecture of an intelligent human-like agent with multiple independent dynamically changing motives in a dynamically changing only partly predictable world. The architecture proposed includes a combination of reactive, deliberative and meta-management mechanisms along with one or more global ``alarm'' systems. The engineering design requirements are discussed in relation our evolutionary history, evidence of brain function and recent theories of Damasio and others about the relationships between intelligence and emotions. (The paper was completed in haste for a deadline and I forgot to explain why Descartes was in the title. See Damasio 1994.).

This paper offers a short and biased overview of the history of discussion and controversy about the role of different forms of representation in intelligent agents. It repeats and extends some of the criticisms of the `logicist' approach to AI that I first made in 1971, while also defending logic for its power and generality. It identifies some common confusions regarding the role of visual or diagrammatic reasoning including confusions based on the fact that different forms of representation may be used at different levels in an implementation hierarchy. This is contrasted with the way in the use of one form of representation (e.g. pictures) can be {\em controlled} using another (e.g. logic, or programs). Finally some questions are asked about the role of metrical information in biological visual systems.

There is now a huge amount of interest in consciousness among scientists as well as philosophers, yet there is so much confusion and ambiguity in the claims and counter-claims that it is hard to tell whether any progress is being made. This ``position paper'' suggests that we can make progress by temporarily putting to one side questions about what consciousness is or which animals or machines have it or how it evolved. Instead we should focus on questions about the sorts of architectures that are possible for behaving systems and ask what sorts of capabilities, states and processes, might be supported by different sorts of architectures. We can then ask which organisms and machines have which sorts of architectures. This combines the standpoint of philosopher, biologist and engineer. If we can find a general theory of the variety of possible architectures (a characterisation of ``design space'') and the variety of environments, tasks and roles to which such architectures are well suited (a characterisation of ``niche space'') we may be able to use such a theory as a basis for formulating new more precisely defined concepts with which to articulate less ambiguous questions about the space of possible minds. For instance our initially ill-defined concept (``consciousness'') might split into a collection of more precisely defined concepts which can be used to ask unambiguous questions with definite answers. As a first step this paper explores a collection of conjectures regarding architectures and their evolution. In particular we explore architectures involving a combination of coexisting architectural levels including: (a) reactive mechanisms which evolved very early, (b) deliberative mechanisms which evolved later in response to pressures on information processing resources and (c) meta-management mechanisms that can explicitly inspect evaluate and modify some of the contents of various internal information structures. It is conjectured that in response to the needs of these layers, perceptual and action subsystems also developed layers, and also that an ``alarm'' system which initially existed only within the reactive layer may have become increasingly sophisticated and extensive as its inputs and outputs were linked to the newer layers. Processes involving the meta-management layer in the architecture could explain the origin of the notion of ``qualia''. Processes involving the ``alarm'' mechanism and mechanisms concerned with resource limits in the second and third layers gives us an explanation of three main forms of emotion, helping to account for some of the ambiguities which have bedevilled the study of emotion. Further theoretical and practical benefits may come from further work based on this design-based approach to consciousness. A deeper longer term implication is the possibility of a new science investigating laws governing possible trajectories in design space and niche space, as these form parts of high order feedback loops in the biosphere

When scientists attempt to explain observations of behaviour in humans and other animals, they often use language that evolved for informal discourse among people engaged in every day social interaction, like this: What does the infant/child/adult/chimp/crow perceive/understand/learn/intend? What is he/she/it conscious of? What does he/she/it experience/enjoy/desire? What is he/she/it attending to? Why did he/she/it do X, start Xing, stop Xing, speed up Xing...? Does he/she/it know that...? What did/does he/she/it expect will happen, if...? Similar comments can be made about the terminology used in many philosophical discussions about minds, cognition, language, and the relationships between evolution and learning

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.

Response to "Predictive Policies" by R.S.McGowan Mr. McGowan has assumed that there is a clear distinction between inductive inferences and others, that we all know how to make the distinction, that we all agree that the inductive ones are somehow better or more reasonable than the alternatives, and I have criticised all of these assumptions. Further he hasformulated the philosophical problem of induction as the problem of showing why the inductive ones are better, and he has attempted to show that inductive policiesas represented in his flow chart are better than non-inductive and counter-inductive ones. I have criticised some of the details of his argument and put forward the counter-claim that policies based on the weaker principles of desistence are better at avoiding contradictions and conform to past experience more closely than policies based on his strong principle of persistence. Accordingly, some modifications of his predictive rules have been suggested. Perhaps most importantly of all, I have argued that the assertion that one policy or inference is better or more rational than another is an incomplete assertion until a basis of comparison has been specified, since different policies may be better or more rational in relation to different bases, and I have indicated some possible approaches for further investigation of this point. A final line of investigation which should be mentioned is the problem of deciding which of two bases of comparison is better relative to some higher-order basis of comparison, a problem which may turn out to be very important in connexion with justifications of predictive policies. It seems that I have asked more questions than I have answered. Perhaps formulating them will help someone more familiar with the field than I am to find interesting answers.

If we are to understand the nature of science, we must see it as an activity and achievement of the human mind alongside others, such as the achievements of children in learning to talk and to cope with people and other objects in their environment, and the achievements of non-scientists living in a rich and complex world which constantly poses problems to be solved. Looking at scientific knowledge as one form of human knowledge, scientific understanding as one form of human understanding, scientific investigation as one form of human problem-solving activity, we can begin to see more clearly what science is, and also what kind of mechanism the human mind is. By undermining the slogan that science is the search for laws, and subsidiary slogans such as that quantification is essential, that scientific theories must be empirically refutable, and that the methods of philosophers cannot serve the aims of scientists, I shall try, in what follows, to liberate some scientists from the dogmas indoctrinated in universities and colleges. I shall also try to show philosophers how they can contribute to the scientific study of man, thereby escaping from the barrenness and triviality complained of so often by non-philosophers and philosophy students. A side-effect which will be reported elsewhere, is to undermine some old philosophical distinctions and pour cold water on battles which rage around them -- like the distinction between subjectivity and objectivity, and the battles between empiricists and rationalists. Key idea: A major aim of science is not to discover and explain laws, but to discover what is possible, and how it is possible. This view of science developed further in Sloman (1978) helps to explain the contributions of Theoretical Linguistics, Chemistry, Artificial Intelligence, and Computer Science insofar as they all enrich our understanding of what is possible and how it is possible. Download: http://www.cs.bham.ac.uk/research/projects/cogaff/papers.html#1976-01

This paper rehearses some relatively old arguments about how any coherent notion of free will is not only compatible with but depends on determinism. However the mind-brain identity theory is attacked on the grounds that what makes a physical event an intended action A is that the agent interprets the physical phenomena as doing A. The paper should have referred to the monograph Intention by Elizabeth Anscombe, which discusses in detail the fact that the same physical event can have multiple descriptions, using different ontologies

[Przekład] To, czego w ciągu ostatnich sześciu lub siedmiu tego nauczyliśmy się na temat wirtualnej maszynerii w wyniku dużego postępu nauki i techniki, umożliwia nam zaoferowanie stanowisku darwinowskiemu nowej obrony przeciw krytykom, którzy twierdzili, że jedynie forma fizyczna – a nie zdolności umysłowe czy świadomość – może być produktem ewolucji poprzez dobór naturalny. Obrona ta porównuje zjawiska umysłowe, wspominane przez przeciwników Darwina, z treściami maszynerii wirtualnej w systemach obliczeniowych. Obiekty, stany, zdarzenia i procesy w owej maszynerii, które dopiero od niedawna umiemy projektować i konstruować, a które nie mogły być nawet przedmiotem rozmyślań w czasach Darwina, mogą współdziałać z maszynerią fizyczną, w której są zaimplementowane, nie będąc identycznymi ze swoją fizyczną implementacją, ani też nie będąc jedynie agregatami fizycznych struktur i procesów. Istnienie różnych rodzajów maszynerii wirtualnej (w tym zarówno „platformowych” maszyn wirtualnych, mogących hostować inne takie maszyny, na przykład systemy operacyjne, jak i „aplikacyjnych” maszyn wirtualnych, na przykład korektorów pisowni i gier komputerowych) zależy od skomplikowanych sieci połączeń przyczynowych związanych ze strukturami hardware’u i software’u, zdarzeniami i procesami, gdzie specyfikacja takich sieci przyczynowych wymaga konceptów, które nie mogą być zdefiniowane w kategoriach konceptów nauk fizycznych. Ta niedefiniowalność, a także możliwość zachodzenia różnych rodzajów automonitorowania w maszynerii wirtualnej, wydaje się wyjaśniać niektóre z rzekomo tajemniczych i nieredukowalnych cech świadomości, które motywowały krytyków Darwina, a także bardziej współczesnych filozofów, krytykujących sztuczną inteligencję. Wynikają z tego konsekwencje dla filozofii, psychologii, neurobiologii i robotyki

The common view that the notion of a Turing machine is directly relevant to AI is criticised. It is argued that computers are the result of a convergence of two strands of development with a long history: development of machines for automating various physical processes and machines for performing abstract operations on abstract entities, e.g. doing numerical calculations. Various aspects of these developments are analysed, along with their relevance to AI, and the similarities between computers viewed in this way and animal brains. This comparison depends on a number of distinctions: between energy requirements and information requirements of machines, between ballistic and online control, between internal and external operations, and between various kinds of autonomy and self-awareness. The ideas are all intuitively familiar to software engineers, though rarely made fully explicit. Most of this has nothing to do with Turing machines or most of the mathematical theory of computation. But it has everything to do with both the scientific task of understanding, modelling or replicating human or animal intelligence and the engineering applications of AI, as well as other applications of computers.

Evolution produced many species whose members are pre-programmed with almost all the competences and knowledge they will ever need. Others appear to start with very little and learn what they need, but appearances can deceive. I conjecture that evolution produced powerful innate meta-knowledge about a class of environments containing 3- D structures and processes involving materials of many kinds. In humans and several other species these innate learning mechanisms seem initially to use exploration techniques to capture a variety of useful generalisations after which there is a "phase transition" in which learnt generalisations are displaced by a new generative architecture that allows novel situations and problems to be dealt with by reasoning -- a pre-cursor to explicit mathematical theorem proving in topology, geometry, arithmetic, and kinematics. This process seems to occur in some non-human animals and in preverbal human toddlers, but is clearest in the switch from pattern-based to syntax-based language use. The discovery of non-linguistic toddler theorems has largely gone unnoticed, though Piaget investigated some of the phenomena, and creative problem solving in some other animals also provides clues. A later evolutionary development seems to have enabled humans to cope with domains that involve both regularities and exceptions, explaining "U-shaped" language learning. Only humans appear to be able to develop meta-meta-competences needed for teaching learnt "theorems" and their proofs. I'll sketch a speculative theory, present examples, and propose a research programme, reducing the 'G' in AGI, while promising increased power in return

This paper is about how to give human-like powers to complete agents. For this the most important design choice concerns the overall architecture. Questions regarding detailed mechanisms, forms of representations, inference capabilities, knowledge etc. are best addressed in the context of a global architecture in which different design decisions need to be linked. Such a design would assemble various kinds of functionality into a complete coherent working system, in which there are many concurrent, partly independent, partly mutually supportive, partly potentially incompatible processes, addressing a multitude of issues on different time scales, including asynchronous, concurrent, motive generators. Designing human like agents is part of the more general problem of understanding design space, niche space and their interrelations, for, in the abstract, there is no one optimal design, as biological diversity on earth shows