Dennett, D. C. 1984 Cognitive wheels: the frame problem of AI. In Minds, machines and evolution (ed. C. Hookway), pp. 129--151. Cambridge University Press.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....were exceedingly limited in their performance: Typically these systems failed as soon as they were faced with real world problems which would take them outside their sheltered artificial world model. One of central problem which causes the failure of AI in the real world is the frame problem [10]: How much information does the algorithm need to cope with all eventualities from the environment This is an unsolvable task for the (external) designer as he she usually can not predict all future situations. The environment it too unpredictable to include all possible environmental influences ....

Daniel C. Dennett. Cognitive wheels: The frame problem of ai. In C. Hookway, editor, Minds, machines, and evolution, pages 129--151. Cambridge University Press, Cambridge, 1984.

....Fodor) has aptly put it. Do something they yelled at it. I am, it retorted. I m busily ignoring some thousands of implications I have determined to be irrelevant. Just as soon as I find an irrelevant implication, I put it on the list of those I must ignore, and. the bomb went off. [27] p.129. It may be that the relevance problem is merely practical, but if so, it is a very deep practical problem that borders on the theoretical. At the very least it is a fundamental issue for any representational system, for at the root of the relevance problem is that most basic question for ....

Daniel C. Dennett. Cognitive wheels: The frame problem of AI. In C. Hookaway, editor, Minds, Machines and Evolution, pages 129-51. Cambridge: Cambridge University Press, 1984.

....in artificial intelligence 73 This is the problem that McCarthy and Hayes (1969) originally called the frame problem . It is, in effect, the problem of finding all the relevant information to the problem in hand, and not getting bogged down explicitly ignoring all the irrelevant information. Dennett (1984) sees this as one aspect of a fundamental new philosophical problem a general epistemological relevance problem one which Hayes calls the whole pudding , but following Dennett I will appropriate the term frame problem for this general relevance problem. The traditional solution to the ....

....a special issue on the differences between minds and computers. 104 Chapter 6 The problems for common sense have generally come in two classes, technical and methodological. On the technical side, for example, there is the frame problem (McCarthy Hayes, 1969) discussed in chapter 4, which Dennett (1984) describes as the smoking pistol behind a lot of the attacks on artificial intelligence, and as a major philosophical problem for everybody. I have already reviewed some of the methodological problems for the different approaches to commonsense reasoning in chapter 4, but, in general, these ....

Dennett, D. C. (1984). Cognitive Wheels: The Frame Problem of AI. In C. Hookway (Ed.), Minds, machines, and evolution (pp. 129-151). Cambridge: Cambridge University Press.

....can provide information about the semantic categories of interest to the user. We emphasized the word correlation to stress the fact that we don t look for an exact correspondence. That would be tantamount to doing unconstrained object recognition: an e#ort bound to incur in the frame problem [6, 1]. We argue that for the retrieval problem a correlation is enough. The user will provide the missing information and the situatedness to drive the system towards the right images. 2 Where did semantics go What the user wants from a database is a semantically meaningful answer to a query. If we ....

Daniel Dennett. Cognitive wheels: the frame problem of AI. In Christopher Hookway, editor, Minds, Machines, and Evolution, Philosophical Studies, pages 129--152. Cambridge University Press, 1984.

....adapt to a situation which was not foreseen by the programmer. Finally, a robot based on a planification relying on symbols has to face sooner or later a combinatoric explosion, because too many alternatives have to be considered in an unpredictable world: this is usually called the frame problem [Den90]. Another issue in such approaches is the fact that the components, their interactions and the internal representation of the world are defined in a rigid manner when constructing the architecture. As this a priori defined representation of the world is arbitrary since it is defined by the ....

D. C. Dennett. Cognitive wheels : the frame problem of AI. In M. A. Boden, editor, The Philosophy of Artificial Intelligence, chapter 7, pages 147--170. Oxford Readings in Philosophy, 1990.

....by the rules used by the system. Since the original article, numerous authors have commented on this problem and, in some cases, presented solutions to it (see, in particular, Lars Erik Janlert, 1987, 1996; Dreyfus Dreyfus, 1987; Haugeland, 1987; etc. In an example very similar to one given by Dennett (1984), a robot is told that its power pack is in a room in which there is a bomb. It is instructed to retrieve its power pack. Its battery is on a small wagon in the room. So it uses its rule PULLOUT(BATTERY, ROOM) to retrieve the battery. It does this by pulling the battery out of the room. But, ....

Dennett, D. (1984). Cognitive wheels: the frame problem of AI. In Minds, Machines and Evolution. C. Hookway (ed.). Cambridge, UK: Cambridge University Press.

....all the different micro worlds. This is the problem that McCarthy and Hayes (1969) originally called the frame problem . It is, in effect, the problem of finding all the relevant information to the problem in hand, and not getting bogged down explicitly ignoring all the irrelevant information. Dennett (1984) sees this as 68 Chapter 4 one aspect of a fundamental new philosophical problem a general epistemological relevance problem one which Hayes calls the whole pudding , but following Dennett I will appropriate the term frame problem for this general relevance problem. The traditional ....

....a special issue on the differences between minds and computers. 100 Chapter 6 The problems for common sense have generally come in two classes, technical and methodological. On the technical side, for example, there is the frame problem (McCarthy Hayes, 1969) discussed in chapter 4, which Dennett (1984) describes as the smoking pistol behind a lot of the attacks on artificial intelligence, and as a major philosophical problem for everybody. I have already reviewed some of the methodological problems for the different approaches to commonsense reasoning in chapter 4, but, in general, these ....

Dennett, D. C. (1984). Cognitive Wheels: The Frame Problem of AI. In C. Hookway (Ed.), Minds, machines, and evolution (pp. 129-151). Cambridge: Cambridge University Press.

....makes the realism projectivism distinction clear and might even indicate or predict the lapse in the classical symbolist program. Dreyfus and Dreyfus (1990) comment upon this (potential) lapse: In the light of this impasse (the common sense knowledge problem, or frame problem (see for example Dennett (1984), R.M. classical, symbol based AI appears more and more to be a perfect example of what Imre Lakatos [ has called a degenerating researchprogramme , p.326, italics added. In terms of Lakatos a degenerating research program is a research program that, after a promising start, has fallen ....

Dennett, D. (1984). Cognitive Wheels: the frame problem of AI. In: Minds, machines and evolution, C. Hookway (ed), Cambridge UP.

.... 1975, Fodor 1981, Cartwright 1983, Horgan Tienson 1989, 1990, Schiffer 1991, Fodor 1991, Dreyfus 1992, Cartwright 1995, Horgan Tienson 1996) I should note that I m concerned with the controversies about ceteris paribus laws that describe human psychology, not the controversies discussed by Dennett (1984) about how human intelligence employs ceteris paribus reasoning. Misgivings about the status of psychological ceteris paribus laws are quite varied, ranging from worries about whether they are trivially or logically or analytically true, to worries about whether they are falsifiable or usable in ....

Dennett, D. C. 1984. Cognitive wheels: the frame problem of AI. In C.

....can provide information about the semantic categories of interest to the user. We emphasized the word correlation to stress the fact that we don t look for an exact correspondence. That would be tantamount to doing unconstrained object recognition: an effort bound to incur in the frame problem [6, 1]. We argue that for the retrieval problem a correlation is enough. The user will provide the missing information and the situatedness to drive the system towards the right images. 2 Where did semantics go What the user wants from a database is a semantically meaningful answer to a query. If we ....

Daniel Dennett. Cognitive wheels: the frame problem of AI. In Christopher Hookway, editor, Minds, Machines, and Evolution, Philosophical Studies, pages 129--152. Cambridge University Press, 1984.

....faster than the human information processor. Another way of looking at this is to say that there is a danger of building cognitive wheels . A cognitive wheel is: Any design proposal in cognitive theory. that is profoundly unbiological, however wizardly and elegant it is as a bit of technology. (Dennett 1984, p. 147) As Clark (1985, 1986) notes, although the mind is treated as a black box system, we at least know that it is a naturally occurring back box . Hence, a biological metaphor is suggested, in which it is insisted that cognitive science be concerned with the development and testing of only ....

Dennett, D. (1984). Cognitive wheels: the frame problem of AI. In Hookway, C., ed, Minds, Machines and Evolution. Cambridge University Press, Cambridge, UK.

....controlled. Likewise, there are some very serious problems when reasoning over abstract symbols. Firstly, the frame problem when deciding to make an action, the reasoning agent should consider the effects of its action upon all of its future actions, lest the action should impede them (see Dennett, 1984, for a detailed consideration) this could lead to an infinite regress of reasoning with no clear way to escape. Secondly, other than Shakey , there is very little evidence that it is possible to obtain an abstract symbolic description of the world in terms of symbols that can be profitably ....

Dennett, D. (1984). Cognitive Wheels: The Frame Problem of AI. In Minds, Machines and Evolution (ed. Hookaway, C.). Cambridge. CUP.

....exactly what is missing in the example of the blackboard: it does not add anything to the input, whereas in a connectionist model the representation is automatically related with similar representations. 8 The frame problem centers around accessibility and relevancy of information or knowledge (Dennett, 1990). In the classical AI model knowledge is stored in the form of explicitly articulated propositions. New information that is fed into the body of knowledge so stored, can and usually does have consequences for the stored knowledge, i.e. some propositions might have to be changed or abandoned. The ....

Dennett, D.C. (1990), Cognitive wheels: The frame problem of AI, reprinted in: Boden, M.A. (Ed.) (1990), The Philosophy of Artificial Intelligence, pp. 147--170

....(ai) and for the purposes of this paper cognitive science and ai will be considered as distinct disciplines. I assume here that the sole domain of cognitive science is psychologically or biologically plausible models of cognitive processing. That is, I assume that the creation of what Dennett [18] calls cognitive wheels 3 is properly only the domain of ai; although, of course, some cognitive wheels may be lurking within the cognitive science canon, yet to be refuted. Computational neuroscience The notes in this section are taken mainly from [52] and various parts of [34] to which the ....

D. Dennett. Cognitive wheels: The frame problem of AI. In C. Hookway, editor, Minds, Machines, and Evolution. Cambridge University Press, Cambridge, 1984.

....problem, one must be able to do at least two things. The first is to say something like everything else remains unchanged, in order to minimize the description about the things that do 1 There is a frame problem in wider sense in which partiality (of information and processing) is the key [Den87, HM90]. However, the frame problem we will consider in this paper is in narrow sense and we will limit ourselves to the description of actions. not change. This notion introduces non monotonicity, when one fails to conclude that something changes due to lack of information. The other is to minimize ....

D.C. Dennett. Cognitive wheels : the frame problem in AI. In Z.W. Pylyshyn, editor, The robot's dilemma : the frame problem in artificial intelligence. Ablex Publishing Corp., 1987.

No context found.

Dennett, D. C. 1984 Cognitive wheels: the frame problem of AI. In Minds, machines and evolution (ed. C. Hookway), pp. 129--151. Cambridge University Press.

No context found.

Daniel C. Dennett. Cognitive Wheels: The Frame Problem of AI, 1999. http:// hps.elte.hu/gk/books/cog/dennett.htm [Last access: 2002-10-18].

No context found.

Daniel Dennett. Cognitive Wheels: The Frame Problem of AI. In C. Hookway, editor, Minds, Machines, and Evolution: Philosophical Studies, pages 129--151. Cambridge U.P., 1984.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC