Simple conceptual graphs are considered as the kernel of most knowledge representation formalisms built upon Sowa's model. Reasoning in this model can be expressed by a graph homomorphism called projection, whose semantics is usually given in terms of positive, conjunctive, existential FOL. We present here a family of extensions of this model, based on rules and constraints, keeping graph homomorphism as the basic operation. We focus on the formal definitions of the different models obtained, including their operational semantics and relationships with FOL, and we analyze the decidability and complexity of the associated problems (consistency and deduction). As soon as rules are involved in reasonings, these problems are not decidable, but we exhibit a condition under which they fall in the polynomial hierarchy. These results extend and complete the ones already published by the authors. Moreover we systematically study the complexity of some particular cases obtained by restricting the form of constraints and/or rules.

The recursive least-squares (RLS) algorithm is one of the most well-known algorithms used in adaptive filtering, system identification and adaptive control. Its popularity is mainly due to its fast convergence speed, which is considered to be optimal in practice. In this paper, RLS methods are used to solve reinforcement learning problems, where two new reinforcement learning algorithms using linear value function approximators are proposed and analyzed. The two algorithms are called RLS-TD(lambda) and Fast-AHC (Fast Adaptive Heuristic Critic), respectively. RLS-TD(lambda) can be viewed as the extension of RLS-TD(0) from lambda=0 to general lambda within interval [0,1], so it is a multi-step temporal-difference (TD) learning algorithm using RLS methods. The convergence with probability one and the limit of convergence of RLS-TD(lambda) are proved for ergodic Markov chains. Compared to the existing LS-TD(lambda) algorithm, RLS-TD(lambda) has advantages in computation and is more suitable for online learning. The effectiveness of RLS-TD(lambda) is analyzed and verified by learning prediction experiments of Markov chains with a wide range of parameter settings. The Fast-AHC algorithm is derived by applying the proposed RLS-TD(lambda) algorithm in the critic network of the adaptive heuristic critic method. Unlike conventional AHC algorithm, Fast-AHC makes use of RLS methods to improve the learning-prediction efficiency in the critic. Learning control experiments of the cart-pole balancing and the acrobot swing-up problems are conducted to compare the data efficiency of Fast-AHC with conventional AHC. From the experimental results, it is shown that the data efficiency of learning control can also be improved by using RLS methods in the learning-prediction process of the critic. The performance of Fast-AHC is also compared with that of the AHC method using LS-TD(lambda). Furthermore, it is demonstrated in the experiments that different initial values of the variance matrix in RLS-TD(lambda) are required to get better performance not only in learning prediction but also in learning control. The experimental results are analyzed based on the existing theoretical work on the transient phase of forgetting factor RLS methods.

We propose a structured approach to the problem of retrieval of images by content and present a description logic that has been devised for the semantic indexing and retrieval of images containing complex objects. As other approaches do, we start from low-level features extracted with image analysis to detect and characterize regions in an image. However, in contrast with feature-based approaches, we provide a syntax to describe segmented regions as basic objects and complex objects as compositions of basic ones. Then we introduce a companion extensional semantics for defining reasoning services, such as retrieval, classification, and subsumption. These services can be used for both exact and approximate matching, using similarity measures. Using our logical approach as a formal specification, we implemented a complete client-server image retrieval system, which allows a user to pose both queries by sketch and queries by example. A set of experiments has been carried out on a testbed of images to assess the retrieval capabilities of the system in comparison with expert users ranking. Results are presented adopting a well-established measure of quality borrowed from textual information retrieval.

We discuss algorithms for estimating the Shannon entropy h of finite symbol sequences with long range correlations. In particular, we consider algorithms which estimate h from the code lengths produced by some compression algorithm. Our interest is in describing their convergence with sequence length, assuming no limits for the space and time complexities of the compression algorithms. A scaling law is proposed for extrapolation from finite sample lengths. This is applied to sequences of dynamical systems in non-trivial chaotic regimes, a 1-D cellular automaton, and to written English texts.

(IKS 2002).

This first part covers mathematical that teachers will find useful.

Recent advances in artificial intelligence, cognitive science, neuroscience and robotics have stimulated the birth and growth of a new research field, known as computational autonomous mental development. Although human mental development is a wellknown subject of study, e.g., in developmental psychology, computational studies of A brief discussion of the subject is available in an article appeared in Science, available electronically at: http://www.cse.msu.edu/dl/SciencePaper.pdf. More than 11.2 Man and Machine Take the Field, red eye, behind which lurked an unfathomable million trucks entered the United David Olson, The Seattle Times (August intelligence. "The soccer games may be the computer has become more alien Service. But help is at hand, just for fun, but the technology used still. Kubrick had no inkling of the thanks to a maturing computer technology to create and operate the players could networked computer, with its potential with the capability of finding also help build robots to rescue victims for massively distributed intelligence. Known as machine learning president of the RoboCup Federation." of the grander design, just as a or neural networks, such technology Robots Scour WTC Wreckage, Leander single ant has no comprehension of uses the power of computer processing Kahney, Wired News (September the intelligence of the colony.

The AAAI Press - Distributed by The MIT Press Massachusetts Institute of Technology, 5 Cambridge Center, Cambridge, Massachusetts 02142 To order, call toll free: (800) 356-0343 or (617) 625-8569. SPRING 2002 5 first time that AAAI's National conference has been held in Canada--a In addition, the program chairs are experimenting with a new format for AAAI.

Thus, the reader is able to experiment is a logical consequence of a set of aspects of the deduction steps as both a user and a developer statements (the axioms and hypotheses).

As a result, they knowledge of an agent (that is, its epistemic coarse-grained level of abstraction, KBwould argue, it is not possible to discuss state) can be characterized as the Ss can be characterized in terms of two the knowledge of a system independently collection of all possible worlds that components: (1) a knowledge base, encoding of the task context in which are consistent with the knowledge the knowledge embodied by the system is meant to operate. I won't held by the agent. If the knowledge of the system, and (2) a reasoning engine, go into too many details here because the agent is complete, then the epistemic which is able to query the knowledge a detailed discussion of the declarative state contains only one world. A base, infer or acquire knowledge from versus the procedural argument is well nice feature of Levesque and Lakemeyer's external sources, and add new knowledge beyond the scope of this review. The treatment of epistemic logic is that to the knowledge base. Levesque important point to make is that in contrast to many other treatments and Lakemeyer's The Logic of Knowledge Levesque and Lakemeyer's approach is of modalities, the discussion is reasonably Bases deals with the "internal logic" of situated in a precise AI research easy to follow for people who are a KBS: It provides a formal account of paradigm, which considers knowledge not experts in the field. This is the result the interaction between a reasoning bases as declaratively specified, task-independent of two main features of this analysis: engine and a knowledge base.