A semantic network or net is a graphic notation for representing knowledge in patterns of interconnected nodes and arcs. Computer implementations of semantic networks were first developed for artificial intelligence and machine translation, but earlier versions have long been used in philosophy, psychology, and linguistics. What is common to all semantic networks is a declarative graphic representation that can be used either to represent knowledge or to support automated systems for reasoning about knowledge. Some versions are highly informal, but other versions are formally defined systems of logic. Following are six of the most common kinds of semantic networks, each of which is discussed in detail in one section of this article. 1. Definitional networks emphasize the subtype or is-a relation between a concept type and a newly defined subtype. The resulting network, also called a generalization or subsumption hierarchy, supports the rule of inheritance for copying properties defined for a supertype to all of its subtypes. Since definitions are true by definition, the information in these networks is often assumed to be necessarily true.

Abstract--The recognition of three-dimensional ( 3-D) objects from sequences of their two-dimensional ( 2-D) views is modeled by a family of self-organizing neural architectures, called VIEWNET, that use View Information Encoded With NETworks. VIEWNET incorporates a preprocessor that generates a compressed but 2-D invariant representation of an image, a supervised incremental learning system that classifies the preprocessed representations into 2-1) view categories whose outputs are combined into 3-D invariant object categories, and a working memory that makes a 3-D object prediction by accumulating evidence from 3-D object category nodes us multiple 2-D views are experienced. The simplest VIEWNET achieves high recognition scores without the need to explicitly code the temporal order of 2-D views in working memory. Working memories are also discussed that save memory resources by implicitly coding temporal order in terms of the relative activity of 2-D view category nodes, rather than as explicit 2-D view transitions. Variants of the VIEWNET architecture may be used for scene understanding by using a preprocessor and classifier that can determine both what objects are in a scene and where they are located. The present VIEWNET preprocessor includes the CORT-X 2 filter, which discounts the illuminant, regularizes and completes figural boundaries, and suppresses image noise. This boundary segmentation is rendered invariant under 2-D translation, rotation, and dilation by use of a log-polar transform. The invariant spectra undergo Gaassian coarse coding to further reduce noise and 3-D foreshortening effects, and to increase generalization. These compressed codes are input into the

'K if-I- I r % f7T

Distributed systems are multi-processor information processing systems which do not rely on the central shared memory for communication. The importance of distributed systems has been growing with the advent of "computer

1 An understanding of learning -- the process by which a learner acquires and refines a broad range of knowledge and skills -- is central to the enterprise of building truly adaptive, flexible, robust, and creative intelligent systems. Significant theoretical and empirical contributions to the characterization of learning in computational terms have emerged from research in a number of disparate research paradigms. The limitations of individual paradigms and of particular classes of techniques within each paradigm are beginning to be recognized. Converging lines of evidence from multiple sources, both theoretical as well as empirical, suggest that artificial intelligence systems, in order to be able to deal with complex tasks such as recognizing and describing 3-dimensional objects, or communicating in natural language, must be able to effectively utilize a range of learning algorithms operating with an adequate repertoire of representational structures. This paper draws on a broad ran...

Semantic content analysis differs from traditional computerized content analysis because it operates on the referentially integrated, meaning representation of a text instead of a linear string of words. Rather than assessing the thematic orientation of texts based on the frequencies of word occurrences, this new methodology examines and interprets explicit knowledge representations of texts. There are three phases to a semantic content analysis: ffl Text Representation: the sentences of a text are syntactically parsed and semantically represented to create meaning-rich text models; ffl Classification: the political analyst applies recognizers, designed in advance, to classify relational configurations of words in text models; ffl Inspection: the analyst uses any number of interfaces for inspecting text models to view the classifications. In the RELATUS Natural Language Environment, lexical recognizers "tag" instances of categories by matching constraint descriptions for alternat...

This report describes the domain model used in the German Machine Translation project VERBMOBIL. In order make the design principles underlying the modeling explicit, we begin with a brief sketch of the VERBMOBIL demonstrator architecture from the perspective of the domain model. We then present some rather general considerations on the nature of domain modeling and its relationship to semantics. We claim that the semantic information contained in the model mainly serves two tasks. For one thing, it provides the basis for a conceptual transfer from German to English; on the other hand, it provides information needed for disambiguation. We argue that these tasks pose different requirements, and that domain modeling in general is highly task-dependent. A brief overview of domain models or ontologies used in existing NLP systems confirms this position. We finally describe the different parts of the domain model, explain our design decisions, and present examples of how the information con...

Here we propose an approach to object recognition that facilitates the transition from recognition to understanding. The proposed approach begins by segmenting the images into regions using standard image processing approaches, which are subsequently classified using a discovered fuzzy Cartesian granule feature classifier. Understanding is made possible through the transparent and succinct nature of the discovered models. The recognition of roads in images is taken as an illustrative problem in the vision domain. The discovered fuzzy models while providing high levels of accuracy (97%), also provide understanding of the problem domain through the transparency of the learnt models. The learning step in the proposed approach is compared with other techniques such as decision trees, nave Bayes and neural networks.

The rise of component-based software development has created a need for API documentation. Experience has shown that it is hard to create and maintain precise and readable documentation. Prose documentation can provide a good overview but lacks precision. Formal methods offer precision but the resulting documentation is expensive to write and modify. Worse, few developers have the skill or inclination to read formal documentation. We present a pragmatic solution to the problem of API documentation. We augment the current prose documentation with test cases, including expected outputs, and use the prose plus the test cases as the documentation. Typically there are one or two simple test cases for each likely question about API behavior. With this approach, the documentation is precise, albeit partial. Consistency between code and documentation is guaranteed by running the test cases. The readability of the test cases is of paramount importance because communication with API users is th...

Assume that we are trying to build a visual recognizer for a particular class of objects—chairs, for example—using existing induction methods. Assume the assistance of a human teacher who can label an image of an object as a positive or a negative example. As positive examples, we can obviously use images of real chairs. It is not clear, however, what types of objects we should use as negative examples. This is an example of a common problem where the concept we are trying to learn represents a small fraction of a large universe of instances. In this work we suggest learning with the help of near misses—negative examples that differ from the learned concept in only a small number of significant points, and we propose a framework for automatic generation of such examples. We show that generating near misses in the feature space is problematic in some domains, and propose a methodology for generating examples directly in the instance space using modification operators—functions over the instance space that produce new instances by slightly modifying existing ones. The generated instances are evaluated by mapping them into the feature space and measuring their utility using known active learning techniques. We apply the proposed framework to the task of learning visual concepts from range images.