Learning Distributed Representations of Concepts Using Linear Relational Embedding

Authors:
Alberto Paccanaro;Geoffrey E. Hinton
Affiliations:
-;-
Venue:
IEEE Transactions on Knowledge and Data Engineering
Year:
2001

Citing 5
Cited 6

Recursive distributed representations

Artificial Intelligence - On connectionist symbol processing
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Learning and extracting finite state automata with second-order recurrent neural networks

Neural Computation
Original Contribution: A scaled conjugate gradient algorithm for fast supervised learning

Neural Networks
Learning human-like knowledge by singular value decomposition: a progress report

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10

Finknn: a fuzzy interval number k-nearest neighbor classifier for prediction of sugar production from populations of samples

The Journal of Machine Learning Research
Images, Frames, and Connectionist Hierarchies

Neural Computation
Learning distributed representations of high-arity relational data with non-linear relational embedding

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Learning the systematic transformation of holographic reduced representations

Cognitive Systems Research
Representing objects, relations, and sequences

Neural Computation
A semantic matching energy function for learning with multi-relational data

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 these 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 representation 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.