Learning Distributed Representations for the Classification of Terms

Sperduti, Alessandro; Starita, Antonina; Goller, Christoph

Learning Distributed Representations for the Classification of Terms

Alessandro Sperduti, Antonina Starita, Christoph Goller

Download BibTeX Cite

Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence. Connectionist Models. Pages 509-516.

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 termclassification 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 .

Alessandro Sperduti, Antonina Starita, and Christoph Goller. 1995. Learning Distributed Representations for the Classification of Terms. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, IJCAI-95. IJCAI, 509–516. https://ijcai.org/proceedings/1995/67

@inproceedings{ijcai1995p67,
  title     = {Learning Distributed Representations for the Classification of Terms},
  author    = {Sperduti, Alessandro and Starita, Antonina and Goller, Christoph},
  booktitle = {Proceedings of the Fourteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-95}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Chris S. Mellish},
  pages     = {509--516},
  year      = {1995},
  note      = {Connectionist Models},
  url       = {https://ijcai.org/proceedings/1995/67},
}

TY  - CPAPER
TI  - Learning Distributed Representations for the Classification of Terms
AU  - Sperduti, Alessandro
AU  - Starita, Antonina
AU  - Goller, Christoph
T2  - Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, IJCAI-95
PB  - International Joint Conferences on Artificial Intelligence
PY  - 1995
SP  - 509
EP  - 516
UR  - https://ijcai.org/proceedings/1995/67
ER  -