Hybrid sequential Monte Carlo/Kalman methods to train neural networks in non-stationary environments

João F. G. de Freitas, Mahesan Niranjan, Andrew H. Gee. Hybrid sequential Monte Carlo/Kalman methods to train neural networks in non-stationary environments. In Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '99, Phoenix, Arizona, USA, March 15-19, 1999. pages 1057-1060, IEEE Computer Society, 1999. [doi]

Abstract

Abstract is missing.