Training feed-forward networks with the extended Kalman algorithm

By S. Singhal, L. Wu. 1989

How researchers see this paper

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

The Ideal Continual Learner: An Agent That Never Forgets (2023, methodology): “Inspired by classic works on adaptive filtering (Haykin, 2002) and recursive least-squares (Singhal & Wu, 1989) in signal processing, Zeng et al. (2019) proposed to set the projection matrix to be I − (X(j)1 )> ( X (j) 1 (X (j) 1 ) > + λI )−1 X (j) 1 for the task 1 and update it for later tasks as…”
Continual learning of context-dependent processing in neural networks (2018, methodology): “In practice, Pl can be recursively updated for each task in a way similar to calculating the correlation-inverse matrix P(RLS) = ( ∑n i=1x(i)x T (i)+αI)−1 in the RLS algorithm [16, 18, 19] (see discussion on relationship of OWM and RLS in Supplementary Information).”
Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications (2000, methodology): “These include the extended Kalman learning algorithm (Singhal and Wu, 1989) and the non-linear recursive least-squares learning algorithm and its variations (Kollias and Anastrassiou, 1989).”
Continuous Learning of Context-dependent Processing in Neural Networks (2018, methodology): “s iterative method is essentially the Recursive Least Square (RLS) algorithm [24, 25] (see Methods), which has been used to train feedforward and recurrent neural networks to achieve fast convergence [26, 27], tame chaotic activities [28] and avoid interference between consecutively loaded patterns ”