Nils J. Nilsson

Bio: Nils J. Nilsson is an academic researcher from Stanford University. The author has contributed to research in topics: Inference & First-order logic. The author has an hindex of 37, co-authored 90 publications receiving 28751 citations. Previous affiliations of Nils J. Nilsson include SRI International & Artificial Intelligence Center.

Introduction to the COMTEX Microfiche Edition of the SRI Artificial Intelligence Center: Technical Notes

Abstract: Charles A. Rosen came to SRI in 1957. I arrived in 1961. Between these dates, Charlie organized an Applied Physics Laboratory and became interested in "learning machines" and "self-organizing systems." That interest launched a group that ultimately grew into a major world center of artificial intelligence research - a center that has endured twenty-five years of boom and bust in fashion, has "graduated" over a hundred AI research professionals, and has generated ideas and programs resulting in new products and companies as well as scientific articles, books, and this particular collection itself.

Some Ideas on Information Processing in the Cerebellum

Abstract: Other papers presented at this conference tend to deal either with extremely formalised models of neural networks, or with peripheral processing. Therefore, it may be a useful reminder of how much further such studies have to go if we present here some ideas on information processing in the cerebellum, to emphasize how complicated real neuronic interactions can be, and to emphasize how ignorant we are of “the language of neurons” when we move away from the periphery. Here we attempt to formulate questions rather than provide answers — our hope being that we may remind the theorist of a vast range of exacting problems, and stimulate the biologist to learn new types of experimental questions. Our models are not yet in predictive form, not least because much crucial experimental data is lacking — we hope that experimentalists, reading between the lines, will be prompted to carry out new experiments, and then confront the theorists with the task of appropriately refining our approach. We clearly have a long way to go before we can be satisfied with any models of complex neural structures which are not located in the mainstream of the input and output systems.

In Memoriam: John G. Gaschnig

Abstract: John Gaschnig was best known lately for his work on expert systems, notably the PROSPECTOR geological exploration system developed at SRI Internation.

Learning Strategies for Mid-Level Robot Control: Some Preliminary Considerations and Experiments

Abstract: Versatile robots will need to be programmed, of course. But beyond explicit programming by a programmer, they will need to be able to plan how to perform new tasks and how to perform old tasks under new circumstances. They will also need to be able to learn. In this article, I concentrate on two types of learning, namely supervised learning and reinforcement learning of robot control programs. I argue also that it would be useful for all of these programs, those explicitly programmed, those planned, and those learned, to be expressed in a common language. I propose what I think is a good candidate for such a language, namely the formalism of teleo-reactive (T-R) programs. Most of the article deals with the matter of learning T-R programs. I assert that such programs are PAC learnable and then describe some techniques for learning them and the results of some preliminary learning experiments. The work on learning T-R programs is in a very early stage, but I think enough has been started to warrant further development and experimentation. For that reason I make this article available on the web, but I caution readers about the tentative nature of this work. I solicit comments and suggestions at:

Artificial intelligence, employment, and income

Abstract: Artificial intelligence (AI) will have profound societal effects. It promises potential benefits (and may also pose risks) in education, defense, business, law and science. In this article we explore how AI is likely to affect employment and the distribution of income. We argue that AI will indeed reduce drastically the need of human toil. We also note that some people fear the automation of work by machines and the resulting of unemployment. Yet, since the majority of us probably would rather use our time for activities other than our present jobs, we ought thus to greet the work-eliminating consequences of AI enthusiastically. The paper discusses two reasons, one economic and one psychological, for this paradoxical apprehension. We conclude with discussion of problems of moving toward the kind of economy that will be enabled by developments in AI.

Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference

Abstract: From the Publisher: Probabilistic Reasoning in Intelligent Systems is a complete andaccessible account of the theoretical foundations and computational methods that underlie plausible reasoning under uncertainty. The author provides a coherent explication of probability as a language for reasoning with partial belief and offers a unifying perspective on other AI approaches to uncertainty, such as the Dempster-Shafer formalism, truth maintenance systems, and nonmonotonic logic. The author distinguishes syntactic and semantic approaches to uncertainty—and offers techniques, based on belief networks, that provide a mechanism for making semantics-based systems operational. Specifically, network-propagation techniques serve as a mechanism for combining the theoretical coherence of probability theory with modern demands of reasoning-systems technology: modular declarative inputs, conceptually meaningful inferences, and parallel distributed computation. Application areas include diagnosis, forecasting, image interpretation, multi-sensor fusion, decision support systems, plan recognition, planning, speech recognition—in short, almost every task requiring that conclusions be drawn from uncertain clues and incomplete information. Probabilistic Reasoning in Intelligent Systems will be of special interest to scholars and researchers in AI, decision theory, statistics, logic, philosophy, cognitive psychology, and the management sciences. Professionals in the areas of knowledge-based systems, operations research, engineering, and statistics will find theoretical and computational tools of immediate practical use. The book can also be used as an excellent text for graduate-level courses in AI, operations research, or applied probability.

Genetic Programming: On the Programming of Computers by Means of Natural Selection

Abstract: Background on genetic algorithms, LISP, and genetic programming hierarchical problem-solving introduction to automatically-defined functions - the two-boxes problem problems that straddle the breakeven point for computational effort Boolean parity functions determining the architecture of the program the lawnmower problem the bumblebee problem the increasing benefits of ADFs as problems are scaled up finding an impulse response function artificial ant on the San Mateo trail obstacle-avoiding robot the minesweeper problem automatic discovery of detectors for letter recognition flushes and four-of-a-kinds in a pinochle deck introduction to biochemistry and molecular biology prediction of transmembrane domains in proteins prediction of omega loops in proteins lookahead version of the transmembrane problem evolutionary selection of the architecture of the program evolution of primitives and sufficiency evolutionary selection of terminals evolution of closure simultaneous evolution of architecture, primitive functions, terminals, sufficiency, and closure the role of representation and the lens effect Appendices: list of special symbols list of special functions list of type fonts default parameters computer implementation annotated bibliography of genetic programming electronic mailing list and public repository

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).