Results


SESSION 3 PAPER 4 TWO THEOREMS OF STATISTICAL SEPARABILIiY IN THE PERCEPTRON

Classics (Collection 2)

Frank Rosenblatt, born in New Rochelle, New York, U.S.A., July 11, 1928, graduated from Cornell University in 1950, and received a PhD degree in psychology, from the same university, in 1956. He was engaged in research on schizophrenia, as a Fellow of the U.S. Public Health Service, 1951-1953. He has made contributions to techniques of multivariate analysis, psychopathology, information processing and control systems, and physiological brain models. He is currently a Research Psychologist at the Cornell Aeronautical Laboratory, Inc., in Buffalo, New York, where he Is Project Engineer responsible for Project PARA (Perceiving and Recognizing Automaton). FRANK ROSENBLATT SUMMARY A THEORETICAL brain model, the perceptron, has been developed at the Cornell Aeronautical Laboratory, In Buffalo, New York.


SESSION 1 PAPER CONDITIONAL PROBABILITY COMPUTING IN A NERVOUS SYSTEM

Classics (Collection 2)

Dr. Uttley took an Honours degree in Mathematics at King's College, London where he also took a degree in Psychology and did postgraduate research in Visual Perception. At the Royal Radar establishment he designed and built analogue and digital computers. For the last five years Dr. Uttley has been working on theories of computing in the nervous system. The suggestion is based on the similarity of behaviour of these formal systems and or animals. The design of classification computers is discussed in the first paper; the design of conditional probability computers Is discussed in a third paper (Uttley, 1958, ref. 15); in both papers working models are described.


SESSION 1 PAPER 2 OPERATIONAL ASPECTS OF INTELLECT

Classics (Collection 2)

Dr. MacKay is a lecturer in Physics After graduating from St. Andrew's University in 1943 he spent three years on Radar work with the Admiralty. Since 1946, when he joined the staff of King' s College, he has been active in the development of information theory, with special interest in its bearing on the study of both natural and artificial information-systems. In 1951 a Rockefeller Fellowship enabled him to spend a year working in this field in U.S.A. His experimental work has been mainly concerned at first with highspeed analogue computation, and latterly with the informational organization of the nervous system. D. M. MACKAY SUMMARY THIS paper is concerned with some theoretical problems of securing and evaluating'intelligence' in artificial organisms, - particularly the kind of operational features that distinguish what we call'intellect' from mere ability to calculate. Among those discussed are (a) the ability to take cognizance of the'weight' as well as the structure of Information.


OGS9.pdf

Classics (Collection 2)

AN EVALUATION OF RECENT DEVELOPMENTS IN THE FIELD OF LEARNING MACHINES - Oliver G. Selfridge Lincoln Laboratory*, Massachusetts Institute of Technology When it was suggested that I contribute a paper to this session, I had in mind that I would discuss and try and put into some kind of technological context the other papers of the session. Much of my own work of recent years has been in the field of learning machines, and artificial intelligence. There are some of us who are interested in seeing machines behave intelligently, and some of us who are only interested in having the machine simulate theories about how real brains work. I suppose that the former must predominate here, and I belong to that class myself. It is therefore a reasonable question to ask how we shall recognize intelligent behavior in a machine when we manage to find some.


TRACKING AND TILL: ADAPTATION IN MOVEMENT STRATEGIES Oliver G. Selfridge 3olt 3eranek and Newman Inc Cambridge Mass A1 August 1978 A

Classics (Collection 2)

TRACKING AND TRAILING: ADAPTATION IN MOVEMENT STRATEGIES Introduction "e 4-ure to Call creatures], without profusion, kind, The oroper organ, proper powers assigned; Eecn seeming want compensated of course, e:e with egree of sittness, there of force Scientists and engineers can, I suppose, take heart from?one's opti7is7; and Tathematicians can revel in his promise of linearit7, "force/11 in exact Proportion." To discover what are the proPer organs and taa proper powers, and at has been the nature of the compensation, we need to deal with the complexity of organization and feedback. This may seem to fly in the face of Occam's razor, but sim7)le strategies can produce complex behavior, and some simple behavior may in fact be the not so simple product of interactin7 strategies. There there are common processes at,woCk we should find and (r_:escrie them. This monograph studies the adaptive nature of tracking -- following tracs and trails. It 7,s'ks what an organism needs to know in order ...


BOXES: AN EXPERIMENT IN ADAPTIVE CONTROL

Classics (Collection 2)

BOXES is the name of a computer program. This is what the chess player does when he lumps together large numbers of positions as being'similar' to each other, by neglecting the strategically irrelevant features in which they differ. The resultant small game can be said to be a'model' of the large game. To give a brutally extreme example, consider a specification of chess positions so incomplete as to map from the viewpoint of White the approximately 1050 positions of the large game on to the seven shown in Figure 1. Even this simple classification may have a role in the learning of chess.


26 Some Philosophical Problems from the Standpoint of Artificial Intelligence

Classics (Collection 2)

A computer program capable of acting intelligently in the world must have a general representation of the world in terms of which its inputs are interpreted. Designing such a program requires commitments about what knowledge is and how it is obtained. Thus, some of the major traditional problems of philosophy arise in artificial intelligence. More specifically, we want a computer program that decides what to do by inferring in a formal language that a certain strategy will achieve its assigned goal. This requires formalizing concepts of causality, ability, and knowledge.


AUTOMATIC SPEECH RECOGNITION: A PROBLEM FOR MACHINE INTELLIGENCE

Classics (Collection 2)

Speech recognition by machine has not yet been achieved because no suitable specification of the recognition process has been formulated for the machine. The author outlines the disturbances and constraints found in speech, and goes on to a description of the structure implied by the constraints. This description is a prerequisite of speech recognition for two reasons, first to describe general speech structure in terms which allow knowledge of it to be built into the machine as an aid to the recognition process, secondly to allow a good enough description of the input signal for it to lead to a minimum set of recognition possibilities which includes likely alternatives. The outline is drawn of a hypothetical machine to recognise speech, comprising a basic recogniser working on short segments of acoustic waveform only, on to which may be added further structures to use knowledge of speaker characteristics, speech statistics, syntax rules, and semantics, in order to improve the recognition performance. Some detailed examples of possible structures are given.


card 1 of

Classics (Collection 2)

This manual describes how HFI IOS can be used to capture and explore system designs. Capturing a design r:.:eans that tri: system must retain all the information about a design that the designer has given. This information can Bien he used oy other parts of the system to refine the design so that it can be produced according to the designers wishes. The system should make it as easy as possible for the designer to enter the design information. It should help the designer by providing alternatives to a design.


9 Report 83 44 Stanford KSL

Classics (Collection 2)

Reprinted, with permission, from IEEE Acoustic, Speech and Signal Processing, Spring, 1984. H. Penny Nii Heuristic Programming Project Computer Science Department Stanford University Stanford, Ca. 94305 ABSTRACT In the past fifteen years, artificial intelligence scientists have built several signal interpretation, or understanding, programs. These programs have combined "low" level signal processing algorithms with knowledge representation and reasoning techniques used in knowledge-based. HASP/SIAP is one such program that tries to interpret the meaning of passively collected sonar data. In this paper we explore some of the Al techniques that contribute in the "understanding" process.