By Daniel G. Bobrow
This significant selection of brief essays stories the scope and development of analysis in synthetic intelligence during the last 20 years. Seminal and most-cited papers from the magazine man made Intelligence are revisited via the authors who describe how their examine has been built, either by means of themselves and via others, because the journals first publication.The twenty-eight papers span a wide selection of domain names, together with fact maintainance platforms and qualitative method conception, chemical constitution research, prognosis of defective circuits, and figuring out visible scenes; additionally they span a wide diversity of methodologies, from AI's mathematical foundations to platforms architecture.The quantity is devoted to Allen Newell and concludes with a piece of fourteen essays dedicated to a retrospective at the energy and imaginative and prescient of his work.Sections/Contributors:- synthetic Intelligence in viewpoint, D. G. Bobrow.- Foundations. J. McCarthy, R. C. Moore, A. Newell, N. J. Nilsson, J. Gordon and E. H. Shortliffe, J. Pearl, A. okay. Mackworth and E. C. Freuder, J. de Kleer.- imaginative and prescient. H. G. Barrow and J. M. Tenenbaum, B. ok. P. Horn and B. Schunck, ok. Ikeuchi, T. Kanade.- Qualitative Reasoning. J. de Kleer, okay. D. Forbus, B. J. Kuipers, Y. Iwasake and H. A Simon.- prognosis. R. Davis, M. R. Genesereth, P. Szolovits and S. G. Pauker, R. Davis, B. G. Buchanan and E. H. Shortliffe, W. J. Clancey.- Architectures. J. S. Aikins, B. Hayes-Roth, M. J. Stefik et al.- structures. R. E. Fikes and N. J. Nilsson, E. A Feigenbaum and B. G. Buchanan, J. McDermott. Allen Newell. H. A. Simon, M. J. Stefik and S. W. Smoliar, M. A. Arbib, D. C. Dennett, Purves, R. C. Schank and M. Y. Jona, P. S. Rosenbloom and J. E. Laird, P. E. Agre.
Read Online or Download Artificial Intelligence in Perspective PDF
Similar robotics & automation books
There exists particularly an unlimited literature on cellular robots, protecting basic rules on movement keep watch over and path-planning in indoor environments utilizing ultrasonic/laser transducers. notwithstanding, there's a shortage of books/collective files on imaginative and prescient established navigation of cellular robots and multi-agent platforms.
Many underwater operations that have been as soon as conducted by way of divers can now be performed extra successfully and with much less chance with Remotely Operated autos (ROVs). this is often the 1st ROV 'how-to' handbook for these concerned with smaller remark category ROVs used for surveying, inspection, remark and study reasons.
Microcomputer expertise and micromechanical layout have contributed to fresh quick advances in Robotics. specific advances were made in sensor know-how that let robot structures to collect info and react "intelligently" in versatile production platforms. The research and recording of the knowledge are important to controlling the robotic.
Motor vehicle Dynamics and regulate offers a accomplished assurance of car keep watch over structures and the dynamic versions utilized in the improvement of those regulate platforms. The regulate process purposes lined within the booklet comprise cruise keep an eye on, adaptive cruise regulate, ABS, computerized lane conserving, automatic street structures, yaw balance keep watch over, engine regulate, passive, lively and semi-active suspensions, tire-road friction coefficient estimation, rollover prevention, and hybrid electrical automobiles.
Extra info for Artificial Intelligence in Perspective
This work was supported in part by NSF grant IRI-9157936, AFOSR grant 900136. and by State of California MICRO grants 91-124 and 91-125. Some of these applications are described in a recent tutorial article by Charniak [1). 2A more complete account and an updated bibliography are provided in the revised second printing of my book Probabilistic Reasoning in Intelligence Syste,ns . Cop yrigh ted Material 50 J. Pearl 2. Origins The idea of studying distributed probabilistic computations on graphical models began brewing in my mind in the late 1970s, after I read Rumelhart's paper on reading comprehension .
His key assumption was to identify belief in a hypothesis with the probability that the hypothesis was true given all previous evidence. To calculate the impact of new evidence on the belief of every hypothesis in the hierarchy, he proposed the following. Given a piece of evidence, e, bearing on a set of hypotheses, S, assign to each hypothesis in S the likelihood ratio of S, an estimation of the degree to which the evidence confirms or disconfirms S. The ratio is that of the conditional probabilities, P (e S) ¡P (e notS).
There was a final ingredient in my Orientation to the talk, and hence the paper. Although I believed that all of us in AI and computer science had an essentially correct concept of knowledge, I was acutely aware that knowledge had not been conceptualized explicitly in the literature. The concept was used entirely implicitly in our practice. Indeed, the explicit use of the term knowledge still resided with the philosopherswho, from my perspective, didn't understand at all what knowledge was. In accordance with my own belief that I was not giving a scientific talk, only talking about scientific Cop yrigh ted Material Reflections on the knowledge level 33 matters, I was not about to provide in my talk (and paper) a fully technical treatment of the knowledge level.
Artificial Intelligence in Perspective by Daniel G. Bobrow