Goto

Collaborating Authors

 Genre


Review of Representation and Reality

AI Magazine

Part of the Media Laboratory's Steve Benton on an advanced beammixing information. Like Richard Feynman's heritage (its origins are in the television display), (4) movies two books of memoirs and School of Architecture) is a startling of the future (putting feature-length Gleick's Chaos, this book will be receptivity to the arts, especially movies on laser disks, thereby ushering passed among workers in computer music and the visual arts, and Brand in paperback movies), (5) the visible and engineering departments as a repeatedly returns to this subject.


Review of The Media Lab

AI Magazine

Stewart Brand, of Whole Earth Catalog fame, is a technology enthusiast. In 1986, he spent three months in the fantasyland of his choice, MIT's Media Laboratory (formerly the Architecture Machine Group). In his latest book, The Media Lab: Inventing the Future at MIT (Viking/ Penguin, New York, 1988, 285 pp., $10, ISBN 0-14-009701-5), he tells the world what he found.


Review of Artificial Intelligence: A Knowledge-Based Approach

AI Magazine

To be considered exceptional, a textbook must satisfy three basic requirements. First, it must be authoritative, written by one with a broad range of experience in, and knowledge of, a subject. Second, it must effectively communicate to the reader, in the same manner in which a course instructor must be capable of imparting knowledge to students in a classroom. Third, it must stimulate the reader into thinking more deeply about the subject and into viewing it from fresh perspectives. In Artificial Intelligence: A Knowledge-Based Approach (Boyd and Fraser, Boston, 740 pp., $48.95), author Morris W. Firebaugh has succeeded in meeting each of these requirements.


No Reliance Can Be Placed on Appearance: A Response to Kuipers (Letter to the Editor)

AI Magazine

In a letter to the editor (AI Magazine, Winter 1989), Benjamin Kuipers criticizes various points made in an earlier paper of ours (Akman and ten Hagen 1989). First, a side (nonetheless important) remark: Although Kuipers asserts that he distributes QSIM to interested researchers, our experience has been otherwise. Akman has tried twice to obtain QSIM, without success. Although Kuipers promised to deliver a copy -- QSIM was under revision at the time of Akman's request (this being as early as winter 1988) -- the program was never sent. So much for the availability of QSIM. . . . Kuipers' letter is full of sweeping generalizations that are so much against the nature of scientific enterprise. We should also add that we are disappointed to see Kuipers employing universal truths and unarguable facts such as ". . . if you build the wrong model, the predictions derived from that model are likely to be wrong" or ". . . guarantees of mathematical validity [are] necessary for any science" as his main cheval de bataille. In the following we'll point out, one by one, the weaknesses of QSIM. Our task will be easy since we shall merely reproduce, almost verbatim, Kuipers' own sentences (Kuipers 1986) and, additionally, Janowski's (1987) views. (The latter reference gives an excellent review of QSIM's disadvantages.) Then, we'll let the reader judge.



Representations of Commonsense Knowledge

Classics

A full book, available for free in PDF form.From the preface:A major problem in artificial intelligence is to endow computers with commonsense knowledge of the world and with the ability to use that knowledge sensibly. A large body of research has studied this problem through careful analysis of typical examples of reasoning in a variety of commonsense domains. The immediate aim of this research is to develop a rich language for expressing commonsense knowledge, and inference techniques for carrying out commonsense reasoning. This book provides an introduction and a survey of this body of research. It is, to the best of my knowledge, the first book to attempt this.The book is designed to be used as a textbook for a one-semester graduate course on knowledge representation.Morgan Kaufmann



Neural Network Design and the Complexity of Learning

Classics

MIT Press. See also: A reply to Honavar's book review of Neural Network Design and the Complexity of Learning (https://link.springer.com/article/10.1007%2FBF00993256?LI=true).


Training a 3-Node Neural Network is NP-Complete

Neural Information Processing Systems

We consider a 2-layer, 3-node, n-input neural network whose nodes compute linear threshold functions of their inputs. We show that it is NPcomplete to decide whether there exist weights and thresholds for the three nodes of this network so that it will produce output consistent with a given set of training examples. We extend the result to other simple networks. This result suggests that those looking for perfect training algorithms cannot escape inherent computational difficulties just by considering only simple or very regular networks. It also suggests the importance, given a training problem, of finding an appropriate network and input encoding for that problem. It is left as an open problem to extend our result to nodes with nonlinear functions such as sigmoids.