home
people
the greater gatsby
research
annual report
publications
seminars
travel
vacancies
search
ucl
 

 

 

 

 

Learning Distributed Representations of Concepts Using Linear Relational Embedding

Alberto Paccanaro and Geoffrey Hinton
Gatsby Computational Neuroscience Unit
University College London

Submitted to IEEE Trans. on Knowledge and Data Engineering - Special Issue on 'Connectionists Models for learning in Structured Domains

In this paper we introduce Linear Relational Embedding as a means of learning a distributed representation of concepts from data consisting of binary relations between concepts. The key idea is to represent concepts as vectors, binary relations as matrices, and the operation of applying a relation to a concept as a matrix-vector multiplication that produces an approximation to the related concept.  A repesentation for concepts and relations is learned by maximizing an appropriate discriminative goodness function using gradient ascent.  On a task involving family relationships, learning is fast and leads to good generalization.


Download [ps] [pdf]