From Hopfield nets to recursive networks to graph machines: Numerical machine learning for structured data
Authors:
- Aurélie Goulon-Sigwalt-AbramAGAurélie Goulon-Sigwalt-Abram
- Arthur DupratADArthur Duprat
- Gérard DreyfusGDGérard Dreyfus
- 1 November 2005
- journal article
- Published by Elsevier in Theoretical Computer Science
- Vol. 344 (2-3) , 298-334
Abstract
No abstract availableKeywords
This publication has 45 references indexed in Scilit:
- Wide coverage natural language processing using kernel methods and neural networks for structured dataPattern Recognition Letters, 2005
- A preliminary empirical comparison of recursive neural networks and tree kernel methods on regression tasks for tree structured domainsNeurocomputing, 2005
- Mismatch string kernels for discriminative protein classificationBioinformatics, 2004
- Combining flat and structured representations for fingerprint classification with recursive neural networks and support vector machinesPattern Recognition, 2003
- Adaptive graphical pattern recognition for the classification of company logosPattern Recognition, 2001
- On the approximation capability of recurrent neural networksNeurocomputing, 2000
- On the Computational Power of Neural NetsJournal of Computer and System Sciences, 1995
- Labelling Recursive Auto-associative MemoryConnection Science, 1994
- A Neural Network for the Retrieval of Superimposed Connection PatternsEurophysics Letters, 1987
- The perceptron: A probabilistic model for information storage and organization in the brain.Psychological Review, 1958