Further Cognitive Science - Goldsmiths, University of London
Cognitive Computing 2012 The computer and the mind 6. DREYFUS AND DREYFUS Prof Mark Bishop Overview The paper opens with quote from Wittgenstein: Nothing seems more possible to me than that people someday will come to the definite opinion that there is no copy in the ... nervous system which corresponds to a particular thought, or a particular idea, or memory. Ludwig Wittgenstein, 1948: last writings on the Philosophy of Psychology, Volume 1. And from Rumelhart (& Norman) on distributed representation: Information is not stored anywhere in particular. Rather it is stored everywhere. Information is better thought of as evoked than found. 11/02/20
Rumelhart & Norman, (1981). Albeit that such a distributed representation remains spatially located. (c) Bishop: The computer and the mind 2 Symbols and Connections In the late 1940s and early 1950s, people realised computers can do more than just perform arithmetic. In 1950 Turing published his seminal paper Computing Machinery & Intelligence on Artificial Intelligence (AI) which took seriously the notion that one day we would speak of machines thinking without fear of contradiction. From the 1950s two schools of (Artificial) Intelligence (AI) emerged: Symbolic intelligence: Easiest to instantiate a formal world model; Philosophically rationalist & reductionist. Connectionist intelligence: Easiest to model the mind (as interactions of neurons); Philosophy holistic; linked to cognitive neuroscience.
11/02/20 (c) Bishop: The computer and the mind 3 Symbols and intelligence Symbolists view minds & computers as physical-symbol systems Newell & Simons hypothesis This idea is philosophically grounded upon work of Frege, Russell & (early) Whitehead Which are in turn heir to the atomistic reductionist tradition in philosophy. 11/02/20 (c) Bishop: The computer and the mind 4 Atomism and reductionism: Descartes & Hobbes
From Descartes: Understanding as the forming and manipulation of appropriate mental representations formed from primitive elements, naturas simplices - simple elements And all phenomena are understood as combinations of these. From Hobbes: 11/02/20 We deduce that these simple elements were formal and related by purely syntactic - rule based operations; Hence all reasoning is reducible to calculation; ratiocination. (c) Bishop: The computer and the mind 5 The symbolist A.I. research programme
From Leibniz To avoid an infinite regress there must be at base simple elements which represent things in the world, and which are mixed together to define complex objects an alphabet of human thought. From (early) Wittgenstein The picture theory of meaning (atomistic; as defined in the Tractatus) World is the totality of facts, not of things; Such facts are logically described via (syntactic) pictures; Elements of such pictures being combined in definite ways to represent the ways things are combined; The Tractatus was seen as the culmination of the rationalist tradition. Symbolic AI is the attempt to find such primitive elements; 11/02/20
Newell & Simons hypothesis effectively turns Wittgensteins early vision into an empirical claim and bases a research programme on it. (c) Bishop: The computer and the mind 6 The opposing tradition Took inspiration from neuroscience not philosophy ... E.g. Hebbs early work on machine learning; Hebbian learning. And Rosenblatt, who conceived that it would be easier to formalise the brain and then investigate its behaviour, rather than attempt to formalise behaviour and then design an axiomatic system to implement it. 11/02/20 (c) Bishop: The computer and the mind 7 A declaration of war ! It is possible to consider the symbolists as people
building problem solving machines. Whereas connectionists wanted to build systems to generate their own behaviour. Initially both systems appeared successful: 11/02/20 as early as 1958 Herbert Simon claimed he had machine that can think .. .. and by 1959 Rosenblatt publicised much the same opinion of his machines. (c) Bishop: The computer and the mind 8 Problems for A.I. Following the publication of Minsky and Papert's monograph Perceptrons, the symbolists seemed set to win the war of A.I. Yet both traditions had their detractors:
Connectionism via Minsky and Paperts 1969 book, Perceptrons. Symbolism via: The 1973 UK Lighthill Report, Artificial Intelligence: A General Survey, James Lighthill, Artificial Intelligence: a paper symposium, [UK] Science Research Council. Dreyfus, Hubert (1972), What Computers Can't Do, MIT Press. And the detractors essentially much made the same point: 11/02/20 That extant A.I. systems only work on TOY problems. (c) Bishop: The computer and the mind 9 A philosophical crusade Minsky and Papert's attack was seen by some as a philosophical
crusade: M&Ps 1969 analysis was only of Single Layer Perceptrons and yet it succeeded in virtually stopping all research into connectionism: reductionism was being challenged by evil neural holism; atomists need hidden nodes to refer to symbolic [micro] features of environment connectionists are not so committed. Rosenblatts neural research was discredited and connectionism was not even mentioned in early edition of Margaret Bodens seminal text on AI, AI and natural man. However there are other reasons for this prejudice: 11/02/20 With only limited computing power early symbolists could do more; There is a persistent belief that thinking and pattern recognition are separate and that thinking is more important. (c) Bishop: The computer and the mind 10
Atomism in A.I. The underlying philosophical idea - from Plato through Leibniz - is that understanding a domain entails having a context free theory of the domain; enabling [relatively] easy knowledge transfer from one domain to another. Winograd famously described A.I. as an attempt to find a formalism for knowledge, identify the atoms from which it is built and the forces that act upon it. At the time no one specifically argued for atomism in AI, there just remains an implicit assumption that, because it works in other domains it will work here. 11/02/20 (c) Bishop: The computer and the mind 11 Problems for simple atomism / reductionism However the conclusions of later Wittgenstein
After publishing The Tractatus, Wittgenstein spent several years doing phenomenology looking for base atoms of meaning - yet ended up abandoning rationalist philosophy altogether. And the work of early Heidegger For Heidegger traditional philosophy is defined from the start by its focusing on facts (in the world) while "passing over" the world as such. I.e. For Husserl, an act of consciousness noesis - does not grasp onto the object itself, (which is famously left bracketed), but the noema - an abstract form (effectively a hierarchical representation of facts [of the world]) correlated with the act [of directed consciousness]. Whereas Heidegger reasoned that it was fundamentally impossible to find such context-free elements of meaning - facts [of the world] - because depriving any element of its context passing over the world deprives it of the very organisation that makes possible its [veridical] use. And this boded ill for simple reductionism! 11/02/20 (c) Bishop: The computer and the mind
12 Husserls Phenomenolgy For Husserl: An act has directedness only because of the intellectual reasons that give it meaning; Ones predicate senses somehow pick out an objects atomic properties [facts] which are subsequently hierarchically combined to form complex descriptions of objects in the world; 11/02/20 At the top level there is effectively a rule defining all the features - and properties - that can be possibly part of this type of object .. .. a system analogous to Marvin Minskys concept of Frames a knowledge representation systems in classical AI. (c) Bishop: The computer and the mind 13
Heidegger In contrast to Husserl, Heidegger suggests there are other ways of encountering things other than as objects defined by a set of predicates (context free facts) For Heidegger in [trouble free] use; smooth coping A mode of engagement Heidegger calls the ready-to-hand; When things go awry (e.g. the nail breaks; the wall is too solid and requires a heavier hammer) Heidegger refines the mode-of-engagement to the un-ready-to-hand). everyday objects hammers; door knobs etc. - are defined by a context of normative social roles (the manifold assignments of in-order-to ) A mode of engagement Heidegger calls the present to hand. I.e. In the everyday ready-to-hand use of a hammer we actualise a skill with no clear division of subject and object (represented in the mind) in the context of a socially organized nexus of equipment, purposes, and human roles. and the sight with which they accommodate themselves is
circumscription , (Heidegger). 11/02/20 (c) Bishop: The computer and the mind 14 A context free theory of the world ? Can there be a context free theory of the world or is the common-sense background rather an impenetrable ensemble of skills, practises and judgements which cannot be explained in terms of rules? Husserl sought to answer this by asserting that the background is just the interaction of millions upon millions of rule-based axiomatic beliefs (which have truth conditions; and are facts if true): However by the age of 75 Husserl concluded that Phenomenology was an infinite task - as he had to include more and more of a subject's common-sense understanding of the everyday world to describe it So we can characterise the world by detachment from it and then enumerating all such beliefs;
So completing the reductionist, atomistic philosophical task began by Socrates and there is some evidence Minsky felt similar wrt his frame knowledge representation. The naivet of A.I workers regarding (contemporary) philosophical research led Hubert Dreyfus to predict trouble for A.I. (Dreyfus, 1972, What computers cant do); a book [until recently] generally ignored by AI community. 11/02/20 (c) Bishop: The computer and the mind 15 Three stages of (symbolic) AI 1. Representation and search; 2. Facts and rules; but toy micro-worlds did not prove scalable. 3. Common sense knowledge:
Via, for example, means-end analysis. A.I. believes common-sense is formalisable; but need it be? Perhaps common-sense is nothing more than a vast set of special cases ? Is even a naive physics formalisable or does a child perhaps simply learn to discriminate (deploy neural judgement) a large set of special cases? Dreyfuys asserts that, the rationalist tradition has been put to an empirical test and failed Justifying Rosenblatts connectionist approach (re. his intuition that rationalism would be difficult); Now even Terry Winograd has lost faith with A.I. and teaches continental philosophy.. 11/02/20 (c) Bishop: The computer and the mind 16 The new connectionism
Frustrated A.I. workers flock to connectionism: E.g. My own experience at the Oxford Experimental Psychology conference. NB. If the connectionists are correct then philosophers will have to give up the atomistic, logicist, rationalist tradition. Albeit neural-net researchers, influenced by symbolists, have tried to find features of reality in hidden nodes; but this is only true in a trivial sense (by assigning an invented name): Uni-variate neural codes; compare with SDPs bi-variate data. Yet the connectionists only success is also only with limited models; Perhaps connectionism is simply getting a [deserved] chance to fail, like symbolism 11/02/20 (c) Bishop: The computer and the mind 17 Common sense and connectionism The common sense knowledge problem in neural computing is that of generalisation
But what counts as a successful generalisation? The neural-net designer has in mind what is a successful generalisation, but how is this defined? If a classifier network produces an output of an unexpected type, it might have merely learnt a different definition of type to that the designer intended: Ideally in generalising the network can either interpolate between points or extrapolate beyond them; for a neural net to be useful it must be able to generalise in reality an infinite number of curves can go in between and beyond such points; Cf. intelligence tests. Hence in engineering applications the neural network designer determines an architecture to restrict possible transformations, such that net behaves appropriately for the application in mind.
11/02/20 (c) Bishop: The computer and the mind 18 Conclusion If early Heidegger and later Wittgenstein are correct then intelligence is much more holistic (and social) than either connectionism or symbolism imply. Like symbolism, perhaps connectionist systems need to be properly embedded in a social reality to have any chance of making intelligent progress 11/02/20 (c) Bishop: The computer and the mind 19
pour spécifier le facteur d'échelle en puissance de 10. Les nombres complexes utilise les caractères 'i' et 'j' (indifféremment) pour designer la partie imaginaire. Le tableau suivant donne un résumé :
Brazil Geography Brazilian Culture Mixture of African, Portuguese, American Indian, and many other tradition Music & Dance: Samba, Bossa Nova, Capoeira Soccer (known as futebol): Brazil won the World Cup in 2004 Carnival Largest country in Latin America Only Portuguese-speaking...
What is 'problem-solving'? ... Shrek. Draw a picture of Shrek using mainly quadratic curves. ... Implications for pedagogy (summary) Problematising new mathematics: examples. If two numbers add to make 13, and one of them is 8, how can we find...
IF1 IF2 IF3 EF The tetrahedron has three interior faces (IF1, IF2 and IF3) and an exterior face (EF) Not triangular Not an MPG The REL graph of a given a (block) layout may not be an MPG. Layout REL...
The Sikh Religion. over 20 million people worldwide and worlds 5th largest religion. Sikhism preaches a message of devotion and remembrance of God at all times, truthful living, equality of mankind and denounces superstitions and blind rituals.
Posterior or dorsal horns - interneurons and sensory fibers coming from the dorsal root ganglion. ... Neural reflex involves sensory fibers to CNS and motor fibers to effectors. Spinal Reflexes. Five components. Receptor - it is the site of the...
Principe de travail : continuer l'attaque après une esquive Tori attaque O Uchi gari (déséquilibre coté revers)uke esquive et tori enchaine avec O Soto Gari en basculant le déséquilibre cote manche. Tori doit déplacer son pied arrière pour se replacer...
British Literature Honors Notes - Anglo Saxon Literature Anglo Saxon Poetry A lyric poem expresses the thoughts and feelings of a single speaker. Anglo Saxon lyrics, composed for easy memorization and recitation, contain the following elements: regular rhythm, caesuras, kennings,...
Ready to download the document? Go ahead and hit continue!