Enhanced Multi-Stream Kalman Filter Training for Recurrent Networks

By Lee A. Feldkamp, Danil V. Prokhorov, C. Eagen, Fumin Yuan. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. M. C. Ozturk
2. Dongming Xu
3. José Carlos Príncipe
4. Danil V. Prokhorov
5. J. Urgen Schmidhuber
6. Badong Chen
7. Weifeng Liu
8. Benjamin Schrauwen

Citations in the corpus

• Deep learning in neural networks: An overview (2014, neutral): “A combination of a decoupled extended Kalman filter (Kalman, 1960; Williams, 1992b; Puskorius and Feldkamp, 1994; Feldkamp et al., 1998; Haykin, 2001; Feldkamp et al., 2003) and an LSTM RNN (Pérez-Ortiz et al.”
• A Convolutional Learning System for Object Classification in 3-D Lidar Data (2010, methodology): “The subsampling layer uses trainable weights, i.e., the multiplier weight (1/8 in the example above) and the bias weight.”
• Analysis and Design of Echo State Networks (2007, methodology): “Alternative second-order training methods based on extended Kalman filtering (Singhal & Wu, 1989; Puskorius & Feldkamp, 1994; Feldkamp, Prokhorov, Eagen, & Yuan, 1998) and the multistreaming training approach (Feldkamp et al., 1998) provide more reliable performance and have enabled practical applic”