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.

English-to-French I f _[ French-to-English We present an overview of Candide, a system for automatic e Channel " -] Decoder 6 translation of French text to English text.

Vision based mobile robot guidance has proven difficult for classical machine vision methods because of the diversity and real time constraints inherent in the task. This thesis describes a connectionist system called ALVINN (Autonomous Land Vehicle In a Neural Network) that overcomes these difficulties. ALVINN learns to guide mobile robots using the back-propagation training algorithm. Because of its ability to learn from example, ALVINN can adapt to new situations and therefore cope with the diversity of the autonomous navigation task. But real world problems like vision based mobile robot guidance presents a different set of challenges for the connectionist paradigm.

Animal locomotion patterns are controlled by recurrent neural networks called central pattern generators (CPGs). Although a CPG can oscillate autonomously, its rhythm and phase must be well coordinated with the state of the physical system using sensory inputs. In this paper we propose a learning algorithm for synchronizing neural and physical oscillators with specific phase relationships. Sensory input connections are modified by the and input signals. Simulations showcorrelation between cellular activities that the learning rule can be used for setting sensory feedback connections to a CPG as well as coupling connections between CPGs. 1 CENTRAL AND SENSORY MECHANISMS IN LOCOMOTION CONTROL Patterns of animal locomotion, such as walking, swimming, and fiying, are generated by recurrent neural networks that are located in segmental ganglia of invertebrates and spinal cords of vertebrates (Barnes and Gladden, 1985).

Do you want your neural net algorithm to learn sequences? Do not limit yourself to conventional gradient descent (or approximations thereof). Instead, use your sequence learning algorithm (any will do) to implement the following method for history compression. No matter what your final goals are, train a network to predict its next input from the previous ones. Since only unpredictable inputs convey new information, ignore all predictable inputs but let all unexpected inputs (plus information about the time step at which they occurred) become inputs to a higher-level network of the same kind (working on a slower, self-adjusting time scale). Go on building a hierarchy of such networks.

Connections between spline approximation, approximation with rational functions, and feedforward neural networks are studied. The potential improvement in the degree of approximation in going from single to two hidden layer networks is examined. Some results of Birman and Solomjak regarding the degree of approximation achievable when knot positions are chosen on the basis of the probability distribution of examples rather than the function values are extended.

One method proposed for improving the generalization capability of a feedforward network trained with the backpropagation algorithm is to use artificial training vectors which are obtained by adding noise to the original training vectors. We discuss the connection of such backpropagation training with noise to kernel density and kernel regression estimation. We compare by simulated examples (1) backpropagation, (2) backpropagation with noise, and (3) kernel regression in mapping estimation and pattern classification contexts.