The Community for Technology Leaders
Neural Networks, IEEE - INNS - ENNS International Joint Conference on (2000)
Como, Italy
July 24, 2000 to July 27, 2000
ISSN: 1098-7576
ISBN: 0-7695-0619-4
pp: 2259
Alberto Paccanaro , University College London
Geoffrey E. Hinton , University College London
ABSTRACT
Linear Relational Embedding (LRE) was introduced (Paccanaro and Hinton, 1999) as a means of extracting a distributed representation of concepts from relational data. The original formulation cannot use negative information and cannot properly handle data in which there are multiple correct answers. In this paper, we propose an extended formulation of LRE that solves both these problems. We present results in two simple domains, which show that learning leads to good generalization.
INDEX TERMS
CITATION

A. Paccanaro and G. E. Hinton, "Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions," Neural Networks, IEEE - INNS - ENNS International Joint Conference on(IJCNN), Como, Italy, 2000, pp. 2259.
doi:10.1109/IJCNN.2000.857906
94 ms
(Ver 3.3 (11022016))