Dynamic Learning with the EM Algorithm for Neural Networks
Journal of VLSI Signal Processing Systems
A learning algorithm for continually running fully recurrent neural networks
Neural Computation
| Hi-index | 0.00 |
Recurrent Neural Networks have been used extensively for space weather forecasts of geomagnetospheric disturbances. One of the major drawbacks for reliable forecasts have been the use of training algorithms that are unable to account for model uncertainty and noise in data. We propose a probabilistic training algorithm based on the Expectation Maximization framework for parameterization of the model which makes use of a forward filtering and backward smoothing Expectation step, and a Maximization step in which the model uncertainty and measurement noise estimates are computed. Through numerical experimentation it is shown that the proposed model allows for reliable forecasts and also outperforms other neural time series models trained with the Extended Kalman Filter, and gradient descent learning.