Foundations and grand challenges of artificial intelligence
AI MagazinePublished 1 December 1988
Raj Reddy
Citations50
SJR quartileQ2
SJR score0.63
SNIP1.31
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
My thoughts on the recent advances in AI, the insights and theoretical foundations that have emerged out of the past thirty years of stable, sustained, systematic explorations in the authors' field, and the grand challenges motivating the research in this field are shared.
Abstract
AAAI is a society devoted to supporting the progress in science, technology and applications of AI. I thought I would use this occasion to share with you some of my thoughts on the recent advances in AI, the insights and theoretical foundations that have emerged out of the past thirty years of stable, sustained, systematic explorations in our field, and the grand challenges motivating the research in our field.
Keywords
Computer Science
Communications of the ACMRandom sample consensus
25,463 Citations1981Martin A. Fischler, Robert C. Bolles
New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Psychological ReviewThe magical number seven, plus or minus two: Some limits on our capacity for processing information.
17,276 Citations1994George Miller
About some experiments that tested how accurately people can assign numbers to the magnitudes of various aspects of a stimulus, and since the results are analyzed in terms of the concepts of information theory, I shall have to preface my discussion with a few remarks about this theory.
The Quarterly Journal of EconomicsA BEHAVIORAL MODEL OF RATIONAL CHOICE
15,263 Citations1955Herbert A. Simon
IEEE ASSP MagazineAn introduction to hidden Markov models
4,789 Citations1986L. R. Rabiner, Biing‐Hwang Juang
The purpose of this tutorial paper is to give an introduction to the theory of Markov models, and to illustrate how they have been applied to problems in speech recognition.
Neural Darwinism: The Theory Of Neuronal Group Selection
2,537 Citations1987Gerald M. Edelman
Artificial IntelligenceThe knowledge level
2,484 Citations1982Allen Newell
A theory of the nature of knowledge is proposed, namely, that there is another computer system level immediately above the symbol (or program) level and knowledge itself is the processing medium at this level and the principle of rationality plays a central role.
Communications of the ACMComputer science as empirical inquiry
2,299 Citations1976Allen Newell, Herbert A. Simon
Computer science is the study of the phenomena surrounding computers; the machine—not just the hardware, but the programmed, living machine—is the organism the authors study.
IEEE Transactions on Acoustics Speech and Signal ProcessingMinimum prediction residual principle applied to speech recognition
1,613 Citations1975Fumitada Itakura
A computer system is described in which isolated words, spoken by a designated talker, are recognized through calculation of a minimum prediction residual through optimally registering the reference LPC onto the input autocorrelation coefficients using the dynamic programming algorithm.
DSpace@MIT (Massachusetts Institute of Technology)MACHINE PERCEPTION OF THREE-DIMENSIONAL SOLIDS,
1,463 Citations1963Lawrence G. Roberts
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering, 1963.
ACM Computing SurveysThe Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty
1,341 Citations1980Lee D. Erman, Frederick Hayes‐Roth +2 more
The characteristics of the speech problem in particular, the special kinds of problem-solving uncertainty in that domain, the structure of the Hearsay-II system developed to cope with that uncertainty, and the relationship between Hearsey-II's structure and those of other speech-understanding systems are discussed.
Cognitive ScienceConnectionist Models and Their Properties
1,324 Citations1982Jerome A. Feldman, D.H. Ballard
A general connectionist model is introduced and how it might be used in cognitive science is considered, among the issues addressed are: stability and noise-sensitivity, distributed decision-making, time and sequence problems, and the representation of complex concepts.
IEEE Transactions on ComputersThe Representation and Matching of Pictorial Structures
1,313 Citations1973Martin A. Fischler, R.A. Elschlager
The primary problem dealt with in this paper is the specification of a descriptive scheme, and a metric on which to base the decision of "goodness" of matching or detection.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Maximum Likelihood Approach to Continuous Speech Recognition
1,220 Citations1983L.R. Bahl, Frederick Jelinek +1 more
This paper describes a number of statistical models for use in speech recognition, with special attention to determining the parameters for such models from sparse data, and describes two decoding methods appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks.
Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)Distributed representations
1,043 Citations2014Geoffrey E. Hinton
Artificial IntelligenceAn analysis of alpha-beta pruning
1,003 Citations1975Donald E. Knuth, Ronald W. Moore
Proceedings of the IEEEContinuous speech recognition by statistical methods
901 Citations1976F. Jelinek
Experimental results are presented that indicate the power of the methods and concern modeling of a speaker and of an acoustic processor, extraction of the models' statistical parameters and hypothesis search procedures and likelihood computations of linguistic decoding.
Understanding Line drawings of Scenes with Shadows
879 Citations1975David L. Waltz
A detailed discussion of the standard approach to computer interpretation of line drawings as three-dimensional scenes as well as some alternative approaches to this approach are discussed.
Medical Entomology and ZoologyScientific Discovery: Computational Explorations of the Creative Processes
812 Citations1987Pat Langley, Herbert A. Simon +2 more
Cancer MedicineRECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES
717 Citations1978Harry G. Barrow, Jay M. Tenenbaum
CH25H was revealed to reduce the proliferation, activity, invasion, and migration of LSCC cells while increasing their apoptosis levels, thus enhancing the apoptosis of LSCC cells.
Artificial IntelligenceUnderstanding image intensities
693 Citations1977Berthold K. P. Horn
The gradient space, popularized by Huffman and Mackworth in a slightly different context, is a helpful tool in the development of new methods for exploiting three-dimensional shape information in image intensities.
Artificial IntelligenceNumerical shape from shading and occluding boundaries
675 Citations1981Katsushi Ikeuchi, Berthold K. P. Horn
An iterative method for computing shape from shading using Occluding boundary information iteratively, using occluding boundaries information to supply boundary conditions and good initial values are found at certain points to help reduce the number of iterations required to reach a reasonable solution.
Artificial IntelligenceOn seeing things
674 Citations1971Mark Clowes
It is argued that at least two types of description of the pattern must be utilised if any significant pattern generalisation is to be achieved, and in general that all picture interpretation tasks involve descriptions in two domains.
IEEE Transactions on Acoustics Speech and Signal ProcessingThe DRAGON system--An overview
508 Citations1975James Baker
This paper briefly describes the major features of the DRAGON speech understanding system, which makes systematic use of a general abstract model to represent each of the knowledge sources necessary for automatic recognition of continuous speech.
Artificial IntelligenceRecovery of the three-dimensional shape of an object from a single view
479 Citations1981Takeo Kanade
The purpose of this paper is to identify some of these assumptions about the world and the image formation process by demonstrating how the theory and techniques which exploit such assumptions can provide a systematic shape-recovery method.
Computer Graphics and Image ProcessingPicture segmentation using a recursive region splitting method
459 Citations1978R. B. Ohlander, Keith Price +1 more
A general segmentation method which can be applied to many different types of scenes and the potential performance of other segmentation techniques on general scenes is discussed.
Elsevier eBooksOn the Role of Structure in Vision
328 Citations1983Andrew Witkin, Jay M. Tenenbaum
It is argued that perceptual organization is a primitive level of inference, the basis for which lies in the relation between structural and causal unity: the appearance of spatiotemporal coherence or regularity is so unlikely to arise by the chance interaction of independent entities that such regular structure, when observed, almost certainly denotes some underlying unified cause or process.
IBM Journal of Research and DevelopmentChess-Playing Programs and the Problem of Complexity
315 Citations1958Allen Newell, James Shaw +1 more
The Los Alamos program is an almost perfect example of the type of system specified by Shannon, and the static evaluation function consisted of a sum of material and mobility measures.
Artificial IntelligenceComputations underlying the measurement of visual motion
300 Citations1984Ellen C. Hildreth
A theoretical analysis of the conditions under which this computation of an instantaneous two-dimensional velocity field yields the correct velocity field suggests that the solution is physically plausible; empirical studies show the results to be consistent with human motion perception.
Artificial IntelligenceInterpreting pictures of polyhedral scenes☆
285 Citations1973Alan Macworth
A computer program that achieves the interpretation of line drawings as polyhedral scenes without using specific object prototypes is described, primarily based on general coherence rules that the orientations of the surfaces and edges must satisfy.
Decomposition of a visual scene into three-dimensional bodies
282 Citations1968Adolfo Guzmán Arenas
This paper describes a program which finds bodies in a scene, presumably formed by three-dimensional objects, and the picture is presented as a line drawing.
Object recognition by affine invariant matching
277 Citations2003Y. Lamdan, Jacob T. Schwartz +1 more
Novel techniques are described for model-based recognition of 3-D objects from unknown viewpoints using single-gray-scale images and efficient matching algorithms are proposed, which assume affine approximation to the perspective viewing transformation.
Philosophical transactions of the Royal Society of London. Series B, Biological sciencesVisual information processing: the structure and creation of visual representations
180 Citations1980David Marr
The Greenblatt chess program
127 Citations1967Richard D. Greenblatt, Donald Eastlake +1 more
The state of the program as of August 1967 is described and some of the details of the heuristics and algorithms employed are given.
Journal of the ACMExperiments With Some Programs That Search Game Trees
118 Citations1969James R. Slagle, John E. Dixon
The problem of efficiently searching large trees is discussed, and a new method called “dynamic ordering” is described, and the older minimax and Alpha-Beta procedures are described for comparison purposes.
USING A COLOR REFLECTION MODEL TO SEPARATE HIGHLIGHTS FROM OBJECT COLOR
105 Citations1987Gudrun Klinker, Steven A. Shafer +2 more
This paper presents a method which exploits the color difference between object color and highlight color, as exhibited in the cluster shape, to separate the color of every pixel into a matte component and a highlight component.
The HWIM speech understanding system
100 Citations2005Jared J. Wolf, William A. Woods
The speech understanding system HWIM is designed to "understand" naturally spoken utterances relevant to a task domain of travel budget management and its performance results at the end of the project are presented.
AI MagazineThe Knowledge Level: Presidential Address
99 Citations1981Allen Newell
Though a president's address cannot be narrow or highly technical, it can certainly address a substantive issue and that is what I propose to do.
IEEE Transactions on Audio and ElectroacousticsA model and a system for machine recognition of speech
94 Citations1973D. R. Reddy, Lee D. Erman +1 more
This paper presents a model for machine recognition of connected speech and the details of a specific implementation of the model, the HEARSAY system, and the use of semantic, syntactic, lexical, and phonological sources of knowledge in the generation and verification of hypotheses.
Outdoor scene analysis using range data
79 Citations1986Martial Hebert
Techniques for outdoor scene analysis using range data are described to build a 3-D representation of the environment of an mobile robot equipped with a range sensor and have been successfully applied to the problem of path planning through obstacles.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThresholding Using Relaxation
76 Citations1981A. Rosenfeld, Russell C. Smith
If a picture contains dark objects on a light background (or vice versa), the objects can be extracted by thresholding, i.e., by classifying the pixels into ``light'' and ``dark'' classes.
Knowledge Level Learning in Soar
67 Citations1987Paul S. Rosenbloom, John E. Laird +1 more
This article demonstrates how Soar can acquire new knowledge that is not deductively implied by its existing knowledge, and employs Soar's chunking mechanism - a mechanism which acquires new productions from goal based experience - as its only learning mechanism.
Elsevier eBooksCOMPUTER CHESS STRENGTH
66 Citations1982Katherine A. Thompson
The most frequently asked question in computer chess is “How strong will chess programs become?” this paper describes an experiment to address this question.
A real-time, isolated-word, speech recognition system for dictation transcription
32 Citations2005F. Jelinek
The architecture of an experimental, real-time, isolated-word, speech recognition system with a 5,000-word vocabulary which can be used for dictating office correspondence is described and some recent experimental results obtained are given.
ICGA JournalSingular Extensions: Adding Selectivity to Brute-Force Searching1
30 Citations1988Thomas Anantharaman, Murray Campbell +1 more
This paper describes a modification of brute-force search, singular extensions, that allows extensions to be identified in a dynamic, domain-independent, low-overhead manner.
Medical Entomology and ZoologyAll the Right Moves: A VLSI Architecture for Chess
30 Citations1987William Henry Carl Ebeling
All the Right Moves "presents a parallel architecture that makes this tradeoff irrelevant: using the VLSI architecture described in this book, the Hitech chess program is able to search both quickly and knowledgeably.
Communications of the ACMAlgorithm design
26 Citations1987Robert E. Tarjan
The quest for efficiency in computational methods yields not only fast algorithms, but also insights that lead to elegant, simple, and general problem-solving methods.
Communications of the ACMComputer science
23 Citations1987John E. Hopcroft
The continued rapid development of computer science will require an expansion of the science base and an influx of talented new researchers to elevate the knowledge of the world.
AI MagazineI Had a Dream: AAAI Presidential Address, August 1985.
11 Citations1986Woody Bledsoe
Twenty-five years ago I had a dream, a daydream, of a special kind of computer, which had eyes and ears and arms and legs, in addition to its “brain,” and which had the ability to recognize faces, synthesize voice, understand spoken sentences, and translate languages, and things like that.
Elsevier eBooksMultiplicative Speedup of Systems
8 Citations1977R. Reddy, Allen Newell
This paper attempts to show that speedups of several orders of magnitude are possible in systems where a hierarchy of levels exists, typical of these are large complex computer systems such as speech- and image-understanding systems.