Simple recurrent networks as generalized hidden Markov models with distributed representations

Yasubumi Sakakibara, Mostefa Golea

Research output: Contribution to conferencePaperpeer-review

6 Citations (Scopus)

Abstract

We propose simple recurrent neural networks as probabilistic models for representing and predicting time-sequences. The proposed model has the advantage of providing forecasts that consist of probability densities instead of single guesses of future values. It turns out that the model can be viewed as a generalized hidden Markov model with a distributed representation. We devise an efficient learning algorithm for estimating the parameters of the model using dynamic programming. We present some very preliminary simulation results to demonstrate the potential capabilities of the model. The present analysis provides a new probabilistic formulation of learning in simple recurrent networks.

Original languageEnglish
Pages979-984
Number of pages6
Publication statusPublished - 1995 Dec 1
Externally publishedYes
EventProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
Duration: 1995 Nov 271995 Dec 1

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period95/11/2795/12/1

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Simple recurrent networks as generalized hidden Markov models with distributed representations'. Together they form a unique fingerprint.

Cite this