Nonlinear Sciences – Adaptation and Self-Organizing Systems
Scientific paper
2007-06-09
Nonlinear Sciences
Adaptation and Self-Organizing Systems
18 pages, 11 figures
Scientific paper
This paper proposes a novel learning method for a mixture of recurrent neural network (RNN) experts model, which can acquire the ability to generate desired sequences by dynamically switching between experts. Our method is based on maximum likelihood estimation, using a gradient descent algorithm. This approach is similar to that used in conventional methods; however, we modify the likelihood function by adding a mechanism to alter the variance for each expert. The proposed method is demonstrated to successfully learn Markov chain switching among a set of 9 Lissajous curves, for which the conventional method fails. The learning performance, analyzed in terms of the generalization capability, of the proposed method is also shown to be superior to that of the conventional method. With the addition of a gating network, the proposed method is successfully applied to the learning of sensory-motor flows for a small humanoid robot as a realistic problem of time series prediction and generation.
Namikawa Jun
Tani Jun
No associations
LandOfFree
A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-126483