Largely from this Traditionally, systems that automatically and realization--was widely experience, we came to understand generate natural language have deemed more convenient than accurate: the sorts of tasks that a text planner been conceived as consisting of two The components of a generator has to perform: determining which principal components: a text planner should be able to communicate at elements to say, coherently structuring and a realization grammar. Recent any level where their information is the input elements, building advances in the art, especially in the applicable.

Commonsense reasoning about the physical world, as exemplified by "Iron sinks in water" or "If a ball is dropped it gains speed," will be indispensable in future programs. We argue that to make such predictions (namely, envisioning), programs should use abstract entities (such as the gravitational field), principles (such as the principle of superposition), and laws (such as the conservation of energy) of physics for representation and reasoning. These arguments are in accord with a recent study in physics instruction where expert problem solving is related to the construction of physical representations that contain fictitious, imagined entities such as forces and momenta (Larkin 1983). We give several examples showing the power of physical representations.

Commentators on AI converge on two goals they believe define the field: (1) to better understand the mind by specifying computational models and (2) to construct computer systems that perform actions traditionally regarded as mental. We should recognize that AI has a third, hidden, more basic aim; that the first two goals are special cases of the third; and that the actual technical substance of AI concerns only this more basic aim. This third aim is to establish new computation-based representational media, media in which human intellect can come to express itself with different clarity and force. This article articulates this proposal by showing how the intellectual activity we label AI can be likened in revealing ways to each of five familiar technologies.

Giving Is Hard: The Complexity of Linear Navigation and Xiaofeng Chen, Wright State University, 274 SC9j22, Santa Clara, CA 95052.

At their meeting in Milan in 1987, IJCAI Inc. was faced with the issue of multiple submission of papers. IJCAI announces its current policy on this issue through this article. The trustees hope this announcement will encourage a debate from which a consensus can emerge.

It 445 Burgess Drive In spite of the many strong technical was generally agreed that the formalization Menlo Park, CA 94025-3496 results that have been produced, it is of commonsense reasoning (415) 328-3123 still far from clear whether existing should be a top-level item for future approaches are sufficient to formalize research.

Failing to recognize this, significance. All interested readers The medium has misplaced the message understanding intelligence and cognition should be directed to his Ph.D. thesis [that should have appeared in Dr. Franck can be reached is merely irreverent, not irrelevant, per se " As readers can see, quite at the following address Dr. Bruno to AI All I can say is mea Thank you Columbus, OH 43210 culpa, and I hope this letter may help James R Slagle and Michael R. Wick to square things I read with great interest the excellent Information Processing. Engineering" by Ken Forbus in AI manuscript, I somehow managed to Professor Forbus's forceful changed the intended meaning rather Our recent article, entitled "A I personally as published reads: "The goal of these examples of our evaluation process thank him for writing such an eloquent gatherings has been to understand One of these examples involved the Various groups, especially for narrowly defined tasks (expert systems)." Naturally, I would not expect Prof. Forbus to enumerate IIICAD stands for "Intelligent, Integrated, and Interactive CAD" and was CWI is a research AAAI Membership Directory center in pure and applied mathematics An invaluable networking tool, this annual roster of AAAI members and computer science at Amsterdam. You've heard of this AAAI conference-it's the most distinguished Email: paulh@cwi.nl. TR An exciting opportunity to view the latest Al products, services, and CSR8744, CWI, Amsterdam research from industry and the academic community. These are the state-of-the-art research papers presented at the AAAl's A copy of this publication is included in conference Data Description Language for Coding registration; AAAI members not attending the conference may purchase Design Knowledge."

Get Citation Alerts New Citation Alert added!

Causal probabilistic networks have proved to be a useful knowledge representation tool for modelling domains where causal relations in a broad sense are a natural way of relating domain objects and where uncertainty is inherited in these relations. This paper outlines an implementation the HUGIN shell--for handling a domain model expressed by a causal probabilistic network. The only topological restriction imposed on the network is that, it must not contain any directed loops. The approach is illustrated step by step by solving a. genetic breeding problem. A graph representation of the domain model is interactively created by using instances of the basic network components—nodes and arcs—as building blocks. This structure, together with the quantitative relations between nodes and their immediate causes expressed as conditional probabilities, are automatically transformed into a tree structure, a junction tree. Here a computationally efficient and conceptually simple algebra of Bayesian belief universes supports incorporation of new evidence, propagation of information, and calculation of revised beliefs in the states of the nodes in the network. Finally, as an example of a real world application, MUN1N an expert system for electromyography is discussed.IJCAI-89, Vol. 2, pp. 1080–1085

We propose learning rules for recurrent neural networks with high-order interactions between some or all neurons. The designed networks exhibit the desired associative memory function: perfect storage and retrieval of pieces of information and/or sequences of information of any complexity.