scispace - formally typeset
Search or ask a question
Topic

Representation (systemics)

About: Representation (systemics) is a research topic. Over the lifetime, 33821 publications have been published within this topic receiving 475461 citations.


Papers
More filters
Patent
05 Sep 2013
TL;DR: In this paper, a graphical user interface concurrently displays a first icon representing a first object type and a second icon that represents a second object type, and a graphical representation of the relationship type is displayed, visually linking the first icon to the second icon.
Abstract: Techniques for visual data import into an object model are described. A graphical user interface concurrently displays a first icon that represents a first object type and a second icon that represents a second object type. Input defining object-to-data mappings between properties of the object types and structured data of one or more data sources is received. Further input defining a relationship type for relationships between the first object type and the second object type is also received. In response to the second input, a graphical representation of the relationship type is displayed, visually linking the first icon to the second icon. Based at least on the object-to-data mappings, the definition of the relationship type, and the structured data, an object model is created, comprising first objects of the first object type, second objects of the second object type, and relationships between the first objects and the second objects.

116 citations

Book ChapterDOI
01 Jan 1983
TL;DR: In this article, the effects of experience on the representation of a large urban environment, and how experience is manipulated by the use of expert and novice taxi drivers, are discussed. But the focus of the present paper is not on taxi drivers.
Abstract: The issue that guides the present research programme concerns the representation of large-scale environments, environments that are too large to be perceived from a single vantage point. In particular, this paper is concerned with the effects of experience on the representation of a large urban environment, and how experience is manipulated by the use of expert and novice taxi drivers.

116 citations

Journal ArticleDOI
TL;DR: The model using semantic representation as input verifies that more accurate results can be obtained by introducing a high-level semantic representation, and shows that it is feasible and effective to introduce high- level and abstract forms of knowledge representation into deep learning tasks.
Abstract: In visual reasoning, the achievement of deep learning significantly improved the accuracy of results. Image features are primarily used as input to get answers. However, the image features are too redundant to learn accurate characterizations within a limited complexity and time. While in the process of human reasoning, abstract description of an image is usually to avoid irrelevant details. Inspired by this, a higher-level representation named semantic representation is introduced. In this paper, a detailed visual reasoning model is proposed. This new model contains an image understanding model based on semantic representation, feature extraction and process model refined with watershed and u-distance method, a feature vector learning model using pyramidal pooling and residual network, and a question understanding model combining problem embedding coding method and machine translation decoding method. The feature vector could better represent the whole image instead of overly focused on specific characteristics. The model using semantic representation as input verifies that more accurate results can be obtained by introducing a high-level semantic representation. The result also shows that it is feasible and effective to introduce high-level and abstract forms of knowledge representation into deep learning tasks. This study lays a theoretical and experimental foundation for introducing different levels of knowledge representation into deep learning in the future.

116 citations

Book ChapterDOI
07 Mar 2013
TL;DR: The basic function of language is communication as mentioned in this paper, and when the listener succeeds in decoding the message intended by the speaker, the communication has been a success. But exactly how does the speaker package information to make sure that the listener will succeed?
Abstract: The basic function of language is communication. When the listener succeeds in decoding the message intended by the speaker, the communication has been a success. But exactly how does the speaker package information to make sure that the listener will succeed? What does the listener have to do to build up a mental representation that echoes the original representation in the speaker’s mind?

115 citations


Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202225
20211,580
20201,876
20191,935
20181,792
20171,391