MetaCartSign in to MyCiteSeer

Include Citations | Advanced Search | Help

Include Citations | Advanced Search | Help

  A representational architecture for nonmonotonic inheritance structures (1993)

Download:
Download as a PDF | Download as a PS
by Ajit Narayanan
In Gielen and Kappen, editors, Proceedings of ICANN
http://www.ida.his.se/ida/research/tech_reports/reports/tr93/HS-IDA-TR-93-001.ps
Add To MetaCart

Abstract:

This paper describes a connectionist system for representing and reasoning with multiple inheritance structures with exceptions. The representational architecture has three characteristics. First, it merges relational with taxonomic representations. Secondly, it handles conflicts generated by exceptions and the use of multiple superclasses. Thirdly, it uses fully distributed representations. One novel feature is that, since the distributed representation of an entity is influenced by its position in the inheritance structure, representations of assertions are influenced by the context of the entities. An extension to the model which implements and makes use of confluent inference is described. 1 The problem of structured representation Ideally, object-centred representations (e.g. frames, semantic networks) should be hierarchic, with subclasses and instances having no more than one class to which they belong. But commonsense reasoning is littered with examples of multiple inheritance, where a class takes some or all properties of two or more classes (e.g. electric guitars have properties of electrical devices and of guitars). Also, commonsense reasoning makes widespread use of exceptions:

Citations

1177 A logic for default reasoning – Reiter - 1979
516 Features of Similarity – Tversky - 1977
308 Recursive distributed representations – Pollack - 1990
302 Principles of categorization – Rosch - 1978
129 Nonmonotonic reasoning: logical foundations of commonsense – Brewka - 1991
113 Mapping part-whole hierarchies into connectionist network – Hinton - 1990
107 General theory of cumulative inference – Makinson - 1989
60 Learning recursive distributed representations for holistic computation – Chrisman - 1991
58 Implementing semantic networks in parallel hardware – Hinton - 1981
32 The Mathematics of Inheritance – Touretzky - 1986
13 Learning distributed representations of conceptual knowledge and their application to script-based story processing – Lee, Flowers, et al. - 1990
8 Forming global representations with extended backpropagation – Miikkulainen, Dyer - 1988
6 A connectionist model of nonmonotonic reasoning: Handling exceptions in inheritance hierarchies – Bod'en, Narayanan - 1994
6 Parallelism in inheritance hierarchies with exceptions – Cottrell - 1985
5 An attractor neural network model of semantic fact retrieval – Ruppin, Usher - 1990
3 The distributed representation of type and category – Robins - 1989