The notion of an ethical machine can be interpreted in more than one way. Perhaps the most important interpretation is a machine that can generalize from existing literature to infer one or more consistent ethical systems and can work out their consequences. An ultra-intelligent machine should be able to do this, and that is one reason for not fearing it.In Hayes, J. E., Michie, D., and Pao, Y.-H. (Eds.), Machine Intelligence 10. Ellis Horwood.

Discourse Processes, vol. 5, No. 1, pp. 1-32.

"An introductory chapter describes the historical and technical foundations of the work .... subsequent chapters describe five prototype computer programs that tackle difficult clinical problems in a manner similar to that of an expert physician. The programs presented are INTERNIST, a diagnostic aid that combines a large database of disease/manifestation associations with techniques for problem formulation; EXPERT and the Glaucoma Program which use physiological models for the diagnosis and treatment of eye disease; MYCIN, a rule-based program for diagnosis and therapy selection for infectious diseases; the Digitalis Therapy Advisor, which aids the physician in prescribing the right dose of the drug digitalis and also explains its actions; and ABEL, a program that uses multi-level pathophysiologic models for diagnosis of acid-base and electrolyte disorders."AAAS Selected Symposia Series, Volume 51. Available from MIT.

This paper describes XSEL, a program being developed at Carnegie-Mellon University that will assist salespeople in tailoring computer systems to fit the needs of customers. XSEL will have two kinds of expertise: it will know how to select hardware and software components that fulfil the requirements of particular sets of applications, and it will know how to provide satisfying explanations in the computer system sales domainIn Hayes, J. E., Michie, D., and Pao, Y.-H. (Eds.), Machine Intelligence 10. Ellis Horwood.

Frogs and toads provide interesting parallels to the way in which humans can see the world about them, and use what they see in determining their actions. What they lack in subtlety of visually-guided behaviour, they make up for in the amenability of their behaviour and the underlying neural circuitry to experimental analysis. This paper presents three specific models of neural circuitry underlying visually-guided behaviour in frog and toad. They form an 'evolutionary sequence' in that each model incorporates its predecessor as a subsystem in such a way as to explain a wider range of behaviour data in a manner consistent with current neurophysiology and anatomy. The models thus form stages in the evolution of Rana computatrix, an increasingly sophisticated model of neural circuitry underlying the behaviour of the frog.In Hayes, J. E., Michie, D., and Pao, Y.-H. (Eds.), Machine Intelligence 10. Ellis Horwood.

ABSTRACT: Objects move, collide, flow, bend, heat up, cool down, stretch, compress . and boil. These and otherthings that cause changes in objects over time are intuitively characterized as processes . To understandcommonsense physical reasoning and make programs that interact with the physical world as well aspeople do we must understand qualitative reasoning about processes, when they will occur, theireffects, and when they will stop. Qualitative process theory defines a simple notion of physical processthat appears useful as a language in which to write dynamical theories. Reasoning about processesalso motivates a new qualitative representation for quantity in terms of inequalities, called thequantity space . This paper describes the basic concepts of qualitative process theory, several differentkinds of reasoning that can be performed with them, and discusses its implications for causalreasoning. Several extended examples illustrate the utility of the theory, including figuring out that aboiler can blow up, that an oscillator with friction will eventually stop, and how to say that you canpull with a string, but not push with it. Journal-length version of Ph.D. dissertation, , MIT, 1985.Artifiicial Intelligence. Also In Bobrow, D. (Ed.), Qualitative Reasoning About Physical Systems, pp. 85–186. MIT Press. Also in Artificial Intelligence 24:85-168 (1984).

In Hayes, J. E., Michie, D., and Pao, Y.-H. (Eds.), Machine Intelligence 10. Ellis Horwood.

Motor control systems are complex systems that process information. Orientation behaviour, posture control, and the manipulation of objects are examples of motor control systems which involve one or more sensory modality and various central neural processes, as well as effector systems and their immediate neuronal control mechanisms. Like all complex information processing systems, they must be analysed and understood at several different levels (see, e.g., Marr & Poggio 1977).At the lowest level there is the analysis of basic components and circuits, the neurons, their synapses, etc. At the other extreme, there is the study of the computations performed by the system — the problems it solves and the ways that it solves them — and the analysis of its logical organization in terms of its primary modules. In Hayes, J. E., Michie, D., and Pao, Y.-H. (Eds.), Machine Intelligence 10. Ellis Horwood.

It appears, however, that we [in AI] are now (finally!) on the verge of practicality in a number of specialities within machine intelligence more or less simultaneously. This can be expected to result in the short term in a qualitative shift in the nature of the field itself, and to result in the longer term in a shift in the way certain industries go about their businessThis paper will discuss three specific areas of work in machine intelligence that MIC [Machine Intelligence Corporation] feels are ripe for commercial application: machine vision, naturallanguage access to computers, and expert systems. It will close with some observations on what makes these areas appropriate for application at this time, and on the difference between a technical solution to a problem and a product.In Hayes, J. E., Michie, D., and Pao, Y.-H. (Eds.), Machine Intelligence 10. Ellis Horwood.

Equation Time Methods Used (I) 2200 Function Swapplng,Polysolve (2) 1905 Function Swapping,Isolation (3) 6280 Homogenization,Function Swapping, (4) I010 (5) 1350 (6) 815 (7) 3580 The numbered equations refer to given in milliseconds. Polysolve,Isolation Homogenization,Polysolve,Isolation Homogenization,Polysolve,Isolation Attraction,Collection,Isolation The following table Homogenlzation,Polysolve,Isolation those given in the introduction. Times are CPU times REFERENCES [Borning and Bundy 81] Borning, A and Bundy, A. Using matching in algebraic equation solving.