Learning distributed representations for the classification of terms

Authors:
Alessandro Sperduti;Antonina Starita;Christoph Goller
Affiliations:
University of Pisa, Dipartimento di Informatica, Pisa, Italy;University of Pisa, Dipartimento di Informatica, Pisa, Italy;Institut für Informatik, Technische Universitat München, München, Germany
Venue:
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
Year:
1995

Citing 2
Cited 8

Recursive distributed representations

Artificial Intelligence - On connectionist symbol processing
Automatic Acquisition of Search Guiding Heuristics

Proceedings of the 10th International Conference on Automated Deduction

Knowledge Extraction from Transducer Neural Networks

Applied Intelligence
Clustering and Classification in Structured Data Domains Using Fuzzy Lattice Neurocomputing (FLN)

IEEE Transactions on Knowledge and Data Engineering
Automatic Adaptation of a Natural Language Interface to a Robotic System

IBERAMIA 2002 Proceedings of the 8th Ibero-American Conference on AI: Advances in Artificial Intelligence
On Linear Separability of Sequences and Structures

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
A flexible multi-layer self-organizing map for generic processing of tree-structured data

Pattern Recognition
On the efficient classification of data structures by neural networks

IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
Learning the systematic transformation of holographic reduced representations

Cognitive Systems Research
Representing objects, relations, and sequences

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper is a study on LRAAM-based (Labeling Recursive Auto-Associative Memory)classification of symbolic recursive structures encoding terms. The results reported here have been obtained by combining an LRAAM network with an analog perceptron. The approach used was to interleave the development of representations (unsupervised learning of the LRAAM) with the learning of the classification task. In this way, the representations are optimized with respect to the classification task. The intended applications of the approach described in this paper are hybrid (symbolic/connectionist) systems, where the connectionist part has to solve logic-oriented inductive learning tasks similar to the term-classification problems used in our experiments. These problems range from the detection of a specific subterm to the satisfaction of a specific unification pattern, and they can get a very satisfactory solution by our approach.