Learning to reproduce fluctuating behavioral sequences using a dynamic neural network model with time-varying variance estimation mechanism

Shingo Murata, Jun Namikawa, Hiroaki Arie, Jun Tani, Shigeki Sugano

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This study shows that a novel type of recurrent neural network model can learn to reproduce fluctuating training sequences by inferring their stochastic structures. The network learns to predict not only the mean of the next input state, but also its time-varying variance. The network is trained through maximum likelihood estimation by utilizing the gradient descent method, and the likelihood function is expressed as a function of both the predicted mean and variance. In a numerical experiment, in order to evaluate the performance of the model, we first tested its ability to reproduce fluctuating training sequences generated by a known dynamical system that were perturbed by Gaussian noise with state-dependent variance. Our analysis showed that the network can reproduce the sequences by predicting the variance correctly. Furthermore, the other experiment showed that a humanoid robot equipped with the network can learn to reproduce fluctuating tutoring sequences by inferring latent stochastic structures hidden in the sequences.

Original languageEnglish
Title of host publication2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings
DOIs
Publication statusPublished - 2013 Dec 31
Externally publishedYes
Event2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Osaka, Japan
Duration: 2013 Aug 182013 Aug 22

Publication series

Name2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings

Conference

Conference2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013
CountryJapan
CityOsaka
Period13/8/1813/8/22

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Software

Fingerprint Dive into the research topics of 'Learning to reproduce fluctuating behavioral sequences using a dynamic neural network model with time-varying variance estimation mechanism'. Together they form a unique fingerprint.

Cite this