Title | ||
---|---|---|
Extracting distributed representations of concepts and relations from positive and negative propositions |
Abstract | ||
---|---|---|
Linear relational embedding (LRE) was introduced previously by the authors (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 |
Year | DOI | Venue |
---|---|---|
2000 | 10.1109/IJCNN.2000.857906 | Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference |
Keywords | Field | DocType |
Gaussian distribution,generalisation (artificial intelligence),learning (artificial intelligence),probability,relational algebra,Gaussian distribution,distributed representations,generalization,learning,linear relational embedding,negative propositions,positive propositions,probability | Codd's theorem,Relational calculus,Embedding,Relational database,Statistical relational learning,Computer science,Theoretical computer science,Relational algebra,Artificial intelligence,Distributed representation,Machine learning | Conference |
Volume | ISSN | ISBN |
2 | 1098-7576 | 0-7695-0619-4 |
Citations | PageRank | References |
5 | 5.69 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alberto Paccanaro | 1 | 206 | 24.14 |
geoffrey e hinton | 2 | 40435 | 4751.69 |