In this paper we consider the problem of `theory patching', in which we are given a domain theory, some of whose components are indicated to be possibly flawed, and a set of labeled training examples for the domain concept. The theory patching problem is to revise only the indicated components of the theory, such that the resulting theory correctly classifies all the training examples. Theory patching is thus a type of theory revision in which revisions are made to individual components of the theory. Our concern in this paper is to determine for which classes of logical domain theories the theory patching problem is tractable. We consider both propositional and first-order domain theories, and show that the theory patching problem is equivalent to that of determining what information contained in a theory is `stable' regardless of what revisions might be performed to the theory. We show that determining stability is tractable if the input theory satisfies two conditions: that revisions to each theory component have monotonic effects on the classification of examples, and that theory components act independently in the classification of examples in the theory. We also show how the concepts introduced can be used to determine the soundness and completeness of particular theory patching algorithms.

We have been conducting research on bottom-up classification techniques ba;ed on trainable artificial neural networks (ANNs), in combination with comprehensive but weakly-applied language models. To focus our work on a subproblem that is tractable enough to le.:'ld to usable products in a reasonable time, we have restricted the domain to hand-printing, so that strokes are clearly delineated by pen lifts. In the process of optimizing overall performance of the recognizer, we have discovered some useful techniques for architecting and training ANNs that must participate in a larger recognition process. Some of these techniques-especially the normalization of output error, frequency balanCing, and error emphal;is-suggest a common theme of significant value derived by reducing the effect of a priori biases in training data to better represent low frequency, low probability smnples, including second and third choice probabilities. There is mnple prior work in combining low-level classifiers with various search strategies to provide integrated segmentation and recognition for writing (Tappert et al 1990) and speech (Renals et aI1992). And there is a rich background in the use of ANNs a-; classifiers, including their use as a low-level, character classifier in a higher-level word recognition system (Bengio et aI1995).

We have been conducting research on bottom-up classification techniques ba;ed on trainable artificial neural networks (ANNs), in combination with comprehensive but weakly-applied language models. To focus our work on a subproblem that is tractable enough to le.:'ld to usable products in a reasonable time, we have restricted the domain to hand-printing, so that strokes are clearly delineated by pen lifts. In the process of optimizing overall performance of the recognizer, we have discovered some useful techniques for architecting and training ANNs that must participate in a larger recognition process. Some of these techniques-especially the normalization of output error, frequency balanCing, and error emphal;is-suggest a common theme of significant value derived by reducing the effect of a priori biases in training data to better represent low frequency, low probability smnples, including second and third choice probabilities. There is mnple prior work in combining low-level classifiers with various search strategies to provide integrated segmentation and recognition for writing (Tappert et al 1990) and speech (Renals et aI1992). And there is a rich background in the use of ANNs a-; classifiers, including their use as a low-level, character classifier in a higher-level word recognition system (Bengio et aI1995).

We have combined an artificial neural network (ANN) character classifier with context-driven search over character segmentation, word segmentation, and word recognition hypotheses to provide robust recognition of hand-printed English text in new models of Apple Computer's Newton MessagePad. We present some innovations in the training and use of ANNs al; character classifiers for word recognition, including normalized output error, frequency balancing, error emphasis, negative training, and stroke warping. A recurring theme of reducing a priori biases emerges and is discussed.

In adjacent agents from dropping their commitments; (held in Kyoto, Japan, on 10-13 December domains (logical philosophy, social or better, how to regulate 1996). Both the program committee philosophy, decision theory), both legal agents dropping their commitments and the contributors included and social norms have received to a joint action to not disrupt the scientists from different backgrounds considerable, if not satisfactory, attention. The discussion addressed on, has contributed dramatically to These tasks have now entered the several issues: (1) What is the the attention given by the scientific MAS field's common knowledge. Often action is reduced to decision authorization, access regulation, For example, the existence of so-called (that is, a choice among one's privacy maintenance, respect of decency, Georgeff 1991) have shown that we and Tennenholtz 1992). Why? Don't we need a reciprocity.

The mail sorting, folding, and inserting mobile personal communications goal is to facilitate the design of exhaust equipment, has implemented an expert network that will permit any mufflers of inlet manifolds in system solution at the core of its type of wireless telephone transmission--voice, hours instead of days. Air Force Manufacturing Technology service data from which common GKIS Intelligent Systems (Houston, Directorate (MANTECH) (Wright-Patterson knowledge--such as service procedures, Tex.) has developed the It is process to prove out and select Intergraph (Huntsville, Ala.), a designed to mine environmental optimal new concepts. The company has Industries (Phenix City, Ala.), a decisions related to advanced launched Project Solomon to upgrade textile manufacturer, is using an automated strike-warfare technology. The Workers' Compensation Fund uses advanced vision technology, neural knowledge-based software. The system compares workers' to develop a fuzzy logic-based solution off-quality production.

The paper describes an extension of well-founded semantics for logic programs with two types of negation. In this extension information about preferences between rules can be expressed in the logical language and derived dynamically. This is achieved by using a reserved predicate symbol and a naming technique. Conflicts among rules are resolved whenever possible on the basis of derived preference information. The well-founded conclusions of prioritized logic programs can be computed in polynomial time. A legal reasoning example illustrates the usefulness of the approach.

To compress text files, a neural predictor network P is used to approximate the conditional probability distribution of possible "next characters", given n previous characters. P's outputs are fed into standard coding algorithms that generate short codes for characters with high predicted probability and long codes for highly unpredictable characters. Tested on short German newspaper articles, our method outperforms widely used Lempel-Ziv algorithms (used in UNIX functions such as "compress" and "gzip").

To compress text files, a neural predictor network P is used to approximate the conditional probability distribution of possible "next characters", given n previous characters. P's outputs are fed into standard coding algorithms that generate short codes for characters with high predicted probability and long codes for highly unpredictable characters. Tested on short German newspaper articles, our method outperforms widely used Lempel-Ziv algorithms (used in UNIX functions such as "compress" and "gzip").

To compress text files, a neural predictor network P is used to approximate theconditional probability distribution of possible "next characters", given n previous characters. P's outputs are fed into standard coding algorithms that generate short codes for characters with high predicted probability and long codes for highly unpredictable characters.Tested on short German newspaper articles, our method outperforms widely used Lempel-Ziv algorithms (used in UNIX functions such as "compress" and "gzip").