TY - GEN
T1 - Learning to reproduce fluctuating behavioral sequences using a dynamic neural network model with time-varying variance estimation mechanism
AU - Murata, Shingo
AU - Namikawa, Jun
AU - Arie, Hiroaki
AU - Tani, Jun
AU - Sugano, Shigeki
PY - 2013/12/31
Y1 - 2013/12/31
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84891133751&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84891133751&partnerID=8YFLogxK
U2 - 10.1109/DevLrn.2013.6652545
DO - 10.1109/DevLrn.2013.6652545
M3 - Conference contribution
AN - SCOPUS:84891133751
SN - 9781479910366
T3 - 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings
BT - 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings
T2 - 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013
Y2 - 18 August 2013 through 22 August 2013
ER -