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.

(IKS 2002).

Serving hors d'oeuvres is not as easy as it might For the fifth five entries took on the challenge of devices were connected to both robots. Mannequins creating service robots who can offer hors were mounted on top of each robot to d'oeuvres to attendees of the robot exhibition. The robots communicated area, find and stop at people to offer food and with each other through a local area network interact with them, detect when more food is on wireless network cards on their laptop computers. For example, Ron Nucci from expected responses. The robot had voice-recognition guest, and serves him/her.

This article is an edited transcript of a lecture given at IJCAI-99, Stockholm, Sweden, on 4 August 1999. The article summarizes concepts, principles, and tools that were found useful in applications involving causal modeling. The principles are based on structural-model semantics in which functional (or counterfactual) relationships representing autonomous physical processes are the fundamental building blocks. The article presents the conceptual basis of this semantics, illustrates its application in simple problems, and discusses its ramifications to computational and cognitive problems concerning causation.

This article presents an overview and survey of current work in case-based reasoning (CBR) integrations. There has been a recent upsurge in the integration of CBR with other reasoning modalities and computing paradigms, especially rule-based reasoning (RBR) and constraint-satisfaction problem (CSP) solving. CBR integrations with modelbased reasoning (MBR), genetic algorithms, and information retrieval are also discussed. This article characterizes the types of multimodal reasoning integrations where CBR can play a role, identifies the types of roles that CBR components can fulfill, and provides examples of integrated CBR systems. Past progress, current trends, and issues for future research are discussed.

Fusions are a simple way of combining logics. For normal modal logics, fusions have been investigated in detail. In particular, it is known that, under certain conditions, decidability transfers from the component logics to their fusion. Though description logics are closely related to modal logics, they are not necessarily normal. In addition, ABox reasoning in description logics is not covered by the results from modal logics. In this paper, we extend the decidability transfer results from normal modal logics to a large class of description logics. To cover different description logics in a uniform way, we introduce abstract description systems, which can be seen as a common generalization of description and modal logics, and show the transfer results in this general setting.

Stimulus arrays are inevitably presented at different positions on the retina in visual tasks, even those that nominally require fixation. In particular, this applies to many perceptual learning tasks. We show that perceptual inference or discrimination in the face of positional variance has a structurally different quality from inference about fixed position stimuli, involving a particular, quadratic, non-linearity rather than a purely linear discrimination. We show the advantage taking this non-linearity into account has for discrimination, and suggest it as a role for recurrent connections in area VI, by demonstrating the superior discrimination performance of a recurrent network. We propose that learning the feedforward and recurrent neural connections for these tasks corresponds to the fast and slow components of learning observed in perceptual learning tasks. 1 Introduction The field of perceptual learning in simple, but high precision, visual tasks (such as vernier acuity tasks) has produced many surprising results whose import for models has yet to be fully felt.

Variational approximations are becoming a widespread tool for Bayesian learning of graphical models. We provide some theoretical results for the variational updates in a very general family of conjugate-exponential graphical models. We show how the belief propagation and the junction tree algorithms can be used in the inference step of variational Bayesian learning. Applying these results to the Bayesian analysis of linear-Gaussian state-space models we obtain a learning procedure that exploits the Kalman smoothing propagation, while integrating over all model parameters. We demonstrate how this can be used to infer the hidden state dimensionality of the state-space model in a variety of synthetic problems and one real high-dimensional data set. 1 Introduction Bayesian approaches to machine learning have several desirable properties.

So which of the two variances is "correct"? From a modelling point of view, the variance from the test example tells us the true story, so the training set variance should be regarded as biased.

Two avenues will be explored: the first is to maximize the ()-average divergence between the class densities and the second is to minimize the union Bhattacharyya bound in the range of (). While both approaches yield similar performance in practice, they outperform standard LDA features and show a 10% relative improvement in the word error rate over state-of-the-art cepstral features on a large vocabulary telephony speech recognition task. 1 Introduction Modern speech recognition systems use cepstral features characterizing the short-term spectrum of the speech signal for classifying frames into phonetic classes. These features are augmented with dynamic information from the adjacent frames to capture transient spectral events in the signal.