A Representational MDL Framework for Improving Learning Power of Neural Network Formalisms

Abstract : Minimum description length (MDL) principle is one of the well-known solutions for overlearning problem, specifically for artificial neural networks (ANNs). Its extension is called representational MDL (RMDL) principle and takes into account that models in machine learning are always constructed within some representation. In this paper, the optimization of ANNs formalisms as information representations using the RMDL principle is considered. A novel type of ANNs is proposed by extending linear recurrent ANNs with nonlinear “synapse to synapse” connections. Most of the elementary functions are representable with these networks (in contrast to classical ANNs) and that makes them easily learnable from training datasets according to a developed method of ANN architecture optimization. Methodology for comparing quality of different representations is illustrated by applying developed method in time series prediction and robot control.
Type de document :
Communication dans un congrès
Lazaros Iliadis; Ilias Maglogiannis; Harris Papadopoulos. 8th International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2012, Halkidiki, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-381 (Part I), pp.68-77, 2012, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-642-33409-2_8〉
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01521390
Contributeur : Hal Ifip <>
Soumis le : jeudi 11 mai 2017 - 17:10:15
Dernière modification le : vendredi 1 décembre 2017 - 01:16:32
Document(s) archivé(s) le : samedi 12 août 2017 - 13:48:11

Fichier

978-3-642-33409-2_8_Chapter.pd...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Alexey Potapov, Maxim Peterson. A Representational MDL Framework for Improving Learning Power of Neural Network Formalisms. Lazaros Iliadis; Ilias Maglogiannis; Harris Papadopoulos. 8th International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2012, Halkidiki, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-381 (Part I), pp.68-77, 2012, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-642-33409-2_8〉. 〈hal-01521390〉

Partager

Métriques

Consultations de la notice

35

Téléchargements de fichiers

23