Showing papers on "Representation (systemics) published in 1994"
TL;DR: A representation of events and action based on interval temporal logic that is significantly more expressive and more natural than most previous AI approaches is presented.
Abstract: We present a representation of events and action based on interval temporal logic that is significantly more expressive and more natural than most previous AI approaches. The representation is motivated by work in natural language semantics and discourse, temporal logic, and AI planning and plan recognition. The formal basis of the representation is presented in detail, from the axiomatization of time periods to the relationship between actions and events and their effects. The power of the representation is illustrated by applying it to the axiomatization and solution of several standard problems from the AI literature on action and change. An approach to the frame problem based on explanation closure is shown to be both powerful and natural when combined with our representational framework. We also discuss features of the logic that are beyond the scope of many traditional representations, and describe our approach to difficult problems such as external events and simultaneous actions.
713 citations
Book•
01 Jan 1994
TL;DR: This work presents a cognitive perspective on knowledge representation from a qualitative perspective and extends the basic model to include qualitative representations of positions in 2-D.
Abstract: Qualitativeness.- A cognitive perspective on knowledge representation.- Qualitative representation of positions in 2-D.- Reasoning with qualitative representations.- Applications.- Extensions of the basic model.- Relevant related work.- Conclusion.
359 citations
Book•
01 Jan 1994
TL;DR: The Role of the Senses in Concept Formation Forms of Representation from Cognition to Curriculum as mentioned in this paper, and the role of the senses in concept formation forms of representation from cognition to curriculum
Abstract: Reforming Educational Reform The Role of the Senses in Concept Formation Forms of Representation From Cognition to Curriculum
303 citations
01 Jan 1994
184 citations
TL;DR: The results demonstrate that the nonprimary auditory thalamus contributes to the generation of a tone-evoked MMN in the guinea pig, and indicate that the Guinea pig is a feasible model for investigating central auditory processes underlying acoustic discrimination.
Abstract: 1. The mismatch response, or mismatch negativity (MMN), is a neurophysiologic response to stimulus change. In humans and other animals, the MMN may underlie the ability to discriminate acoustic dif...
171 citations
TL;DR: A digested compilation of pragmatic concepts and commonly applied techniques concerning genetic algorithms to support the novice practitioner in choosing a representation, a configuration, and, possibly, a hybridization technique for the genetic algorithm applied to the problem of interest.
160 citations
Book Chapter•
01 Jan 1994
154 citations
01 Jan 1994
138 citations
TL;DR: Data from two neuropsychological cases indicating that the allocation of attention in vision is determined by at least two forms of spatial representation are reported, demonstrating that there is parallel coding of visual displays into within- and between-object spatial representations.
Abstract: Our ability both to recognise visually presented objects and to interact with them appropriately depends upon detailed interaction between visual attentional and visual recognition systems. We report data from two neuropsychological cases indicating that the allocation of attention in vision is determined by at least two forms of spatial representation (within-object and between-object spatial coding). In both cases there was unilateral neglect of one side of visual displays if items in the displays were coded as parts of a single perceptual object, and neglect of the opposite side if items were coded as separate perceptual objects. In addition, attentional cueing effects to either the left or right side were specific to the form of representation involved. These cases demonstrate that there is parallel coding of visual displays into within- and between-object spatial representations. Further, visual selection operates independently on the two forms of visual representation. The data support an a...
134 citations
01 Jan 1994
129 citations
Patent•
12 Oct 1994
TL;DR: In this paper, a technique for integrating voxelly-assigned information regarding a portion of anatomy derived from a number of sources into an accurate, single 2D pixel-based representation of a view of that anatomy is disclosed.
Abstract: A technique for integrating voxelly-assigned information regarding a portion of anatomy derived from a number of sources into an accurate, single two dimensional pixel-based representation of a view of that anatomy is disclosed. Empirical relationships between known properties are used to infer values for unknown properties.
TL;DR: Feedforward processing does not deny the possibility that top-down influences, although poorly understood, may play a role in nulling image aspects that are predictable in appearance and/or not the object of attention such that only features containing relevant discriminatory information are processed further.
Book•
01 Jan 1994
Patent•
11 Aug 1994
TL;DR: In this paper, a machine vision system is used to capture an image of the object and convert that image into a digital representation which can then be added to a database to be used to compile an ideal pattern or can be compared to an already existing ideal image to determine if the object is the correct size.
Abstract: An automatic garment inspection and measurement system can create a two-dimensional or three-dimensional electronic representation of an object. This electronic representation can then be combined with other electronic representations to create a database of measurements from which standard patterns can be generated for use in manufacturing garments. The electronic representation can also be used to compare the manufactured object it represents to an ideal representation in order to determine if the object's measurements are within a predetermined tolerance of the ideal representation. A machine vision system is used to capture an image of the object and convert that image into a digital representation which can then be added to a database to be used to compile an ideal pattern or can be compared to an already existing ideal image to determine if the object is the correct size.
Patent•
30 Dec 1994
TL;DR: The Three-dimensional Display as mentioned in this paper is a human/machine interface system that presents information in a three-dimensional and visual form and is optionally capable of receiving input, but it does not support gesture recognition.
Abstract: A human/machine interface system that presents information in a three-dimensional and visual form and is optionally capable of receiving input. The Three-Dimensional Display comprises a display shape with visual displays that is movable to provide visual and three-dimensional representative imagery. An optional method for sensing input can be added to allow user interaction with the display. A number of these displays could be arrayed together and driven by appropriate circuitry to present to the user visual and physical representation upon which the user can act to communicate back to the machine.
01 Jan 1994
TL;DR: For a versatile representation of sensory patterns in the nervous system, three basic functions have been accomplished: elementary features need to be represented by neuronal responses, responses to features constituting a particular object have to be distinguished and bound together in a flexible way, and the specific relations among these features have to been encoded and preserved.
Abstract: Most perceptual objects can be decomposed into components and, in general, the features of these components are not unique for a particular object. The individuality of objects results from the specific composition of elementary features and their relations rather than from the specificity of the component features. Hence, for a versatile representation of sensory patterns in the nervous system, three basic functions have to be accomplished: 1) elementary features need to be represented by neuronal responses, 2) responses to features constituting a particular object have to be distinguished and bound together in a flexible way, and 3) the specific relations among these features have to be encoded and preserved.
Patent•
01 Sep 1994
TL;DR: In this article, an improved system for producing a three-dimensional object by forming successive cross-sections of the object from a material which is normally solid but which may be made flowable, including using data manipulation for converting a 3D object representation into cross-sectional representations.
Abstract: The invention involves an improved system for producing a three-dimensional object by forming successive cross-sections of the object from a material which is normally solid but which may be made flowable, including using data manipulation for converting a three-dimensional object representation into cross-sectional representations.
Patent•
07 Sep 1994TL;DR: In this article, a color original is entered by an input means for prescan, a density distribution with respect to a hue is obtained for each electric signal of color image information, and a characteristic point of the color original image is obtained from the result of the density distribution.
Abstract: The present invention is intended to provide an image processing apparatus capable of two-color output representation in high accuracy even with a full-colored original. A color original is entered by an input means for prescan, a density distribution with respect to a hue is obtained for each electric signal of color image information, and a characteristic point of the color original image is obtained from the result of the density distribution. The two-color separation means separates a full-colored original to two colors free from the same color representation according to the information of the characteristic point obtained.
TL;DR: A framework for thinking about human reasoning about the physical world, and the role played by causal process packages in this framework is described, and various applications of FR are reviewed.
Abstract: Publisher Summary This chapter discusses a theory of representation of causal processes and uses the representational framework for problem solving of various sorts. It presents a framework for thinking about human reasoning about the physical world, and describes the role played by causal process packages in this framework. The chapter gives an informal overview of functional representation (FR) and mentions that FR for a device has three parts: a description of intended function, a description of the structure of the device, and a description of the way the device achieves the function. It lists the component names and their functions and indicates the way the components are put together to make the device. The basic idea in describing the way a device achieves its function is that of a causal process description (CPD). Various applications of FR are reviewed. The organization of a functional representation gives both forward and backward reasoning capability. The chapter describes an algorithm that demonstrates the forward simulation potential.
TL;DR: In this article, the authors present the results of an empirical analysis of six terminological representation systems, including KL-ONE, and the runtime performance of different systems and knowledge bases, and give an idea of what runtime performance to expect from such representation systems.
10 Jul 1994
TL;DR: This paper presents an approach to automatic discovery of functions in Genetic Programming based on discovery of useful building blocks by analyzing the evolution trace, generalizing blocks to define new functions, and adapting the problem representation on-the-fly.
Abstract: This paper presents an approach to automatic discovery of functions in Genetic Programming. The approach is based on discovery of useful building blocks by analyzing the evolution trace, generalizing blocks to define new functions, and finally adapting the problem representation on-the-fly. Adaptating the representation determines a hierarchical organization of the extended function set which enables a restructuring of the search space so that solutions can be found more easily. Measures of complexity of solution trees are defined for an adaptive representation framework. The minimum description length principle is applied to justify the feasibility of approaches based on a hierarchy of discovered functions and to suggest alternative ways of defining a problem's fitness function. Preliminary empirical results are presented.