The field of AI is directed at the fundamental problem of how the mind works; its approach, among other things, is to try to simulate its working -- in bits and pieces. History shows us that mankind has been trying to do this for certainly hundreds of years, but the blooming of current computer technology has sparked an explosion in the research we can now do. The center of AI is the wonderful capacity we call learning, which the field is paying increasing attention to. Learning is difficult and easy, complicated and simple, and most research doesn't look at many aspects of its complexity. However, we in the AI field are starting. Let us now celebrate the efforts of our forebears and rejoice in our own efforts, so that our successors can thrive in their research. This article is the substance, edited and adapted, of the keynote address given at the 1992 annual meeting of the Association for the Advancement of Artificial Intelligence on 14 July in San Jose, California.

If you think this paper has strongly negative effect on the rate of The AAAI Press shortcomings, but its publication progress in the field. However, by all measures the '93 are hashed out in public. "Preliminary work" category were doesn't mean that the author doesn't At the get a fair, public hearing. "innovative" papers was a failure. My explanation of this fact is "expert" bodies in private discussion. General Motors Corporation have read the papers being discussed, around.

Expert systems are technologies to a utility function for generate-andtest the workshop was on the efficiency of support human reasoning by formalizing methods. These methods are conceived managing temporal facts in rulebased expert knowledge so that mechanized as incremental nonheuristic systems. Expert systems that reasoning methods can be algorithms that can be called repeatedly make use of temporal reasoning applied. In real-time systems, these to generate and test a hypothesis.

The Ninth International Conference on Machine Learning was held in Aberdeen, Scotland, from 1-3 July 1992, with 198 participants in attendance. The conference covered a broad range of topics drawn from the general area of machine learning, including concept-learning algorithms, clustering, speedup learning, formal analysis of learning systems, neural networks, genetic algorithms, and applications of machine learning. This article briefly touches on six selected talks that were of exceptional interest.

My Ph.D. dissertation describes PAGODA (probabilistic autonomous goal-directed agent), a model for an intelligent agent that learns autonomously in domains containing uncertainty. The ultimate goal of this line of research is to develop intelligent problem-solving and planning systems that operate in complex domains, largely function autonomously, use whatever knowledge is available to them, and learn from their experience. PAGODA was motivated by two specific requirements: The agent should be capable of operating with minimal intervention from humans, and it should be able to cope with uncertainty (which can be the result of inaccurate sensors, a nondeterministic environment, complexity, or sensory limitations). I argue that the principles of probability theory and decision theory can be used to build rational agents that satisfy these requirements.

Touretzky (1984) proposed a formalism for nonmonotonic multiple inheritance reasoning which is sound in the presence of ambiguities and redundant links. We show that Touretzky's inheritance notion is NPhard, and thus, provided P#NP, computationally intractable. This result holds even when one only considers unambiguous, totally acyclic inheritance networks. A direct consequence of this result is that the conditioning strategy proposed by Touretzky to allow for fast parallel inference is also intractable. Therefore, it follows that nonmonotonic multiple inheritance hierarchies, although compact representations, may not allow for efficient retrieval of information as has been suggested in attempts to use such hierarchies, e.g., in NETL (Fahlman 1979). We also analyze the influence of various design choices made by Touretzky. We show that all versions of downward (coupled) inheritance, i.e., on-path or off-path preemption and skeptical or credulous reasoning, are intractable. However, tractability can be achieved when using upward (decoupled) inheritance.

The field of AI is directed at the fundamental problem of how the mind works; its approach, among other things, is to try to simulate its working -- in bits and pieces. History shows us that mankind has been trying to do this for certainly hundreds of years, but the blooming of current computer technology has sparked an explosion in the research we can now do. The center of AI is the wonderful capacity we call learning, which the field is paying increasing attention to. Learning is difficult and easy, complicated and simple, and most research doesn't look at many aspects of its complexity. However, we in the AI field are starting. Let us now celebrate the efforts of our forebears and rejoice in our own efforts, so that our successors can thrive in their research. This article is the substance, edited and adapted, of the keynote address given at the 1992 annual meeting of the Association for the Advancement of Artificial Intelligence on 14 July in San Jose, California. AI Magazine 14(2): 36-48.

We describe a comprehensive framework for narrative understanding based on Episodic Logic (EL). This situational logic was developed and implemented as a semantic representation and commonsense knowledge representation that would serve the full range of interpretive and inferential needs of general NLU. The most distinctive feature of EL is its natural language-like expressiveness. It allows for generalized quantifiers, lambda abstraction, sentence and predicate modifiers, sentence and predicate reification, intensional predicates (corresponding to wanting, believing, making, etc.), unreliable generalizations, and perhaps most importantly, explicit situational variables (denoting episodes, events, states of affairs, etc.) linked to arbitrary formulas that describe them. These allow episodes to be explicitly related in terms of part-whole, temporal and causal relations. Episodic logical form is easily computed from surface syntax and lends itself to effective inference.

Reinforcement learning is an effective technique for learning action policies in discrete stochastic environments, but its efficiency can decay exponentially with the size of the state space. In many situations significant portions of a large state space may be irrelevant to a specific goal and can be aggregated into a few, relevant, states. The U Tree algorithm generates a tree based state discretization that efficiently finds the relevant state chunks of large propositional domains. In this paper, we extend the U Tree algorithm to challenging domains with a continuous state space for which there is no initial discretization.

Sequencing and scheduling'as a research area is motivated by questions that We review complexity results and'optimization and approximation algorithms The chapter is organized as follows. There are several survey papers that complement the present chapter. In this section, we will review the main points of this theory. NPcompleteness of a particular problem is strong evidence that a polynomial-lime algorithm for its solution is unlikely to exist. The wide applicability of the notion of NPcompleteness was observed by Karp, who proved that 21 basic problems are NPcomplete.