Informative Neural Ensemble Kalman Learning
arXiv:2008.09915
Abstract
In stochastic systems, informative approaches select key measurement or decision variables that maximize information gain to enhance the efficacy of model-related inferences. Neural Learning also embodies stochastic dynamics, but informative Learning is less developed. Here, we propose Informative Ensemble Kalman Learning, which replaces backpropagation with an adaptive Ensemble Kalman Filter to quantify uncertainty and enables maximizing information gain during Learning. After demonstrating Ensemble Kalman Learning's competitive performance on standard datasets, we apply the informative approach to neural structure learning. In particular, we show that when trained from the Lorenz-63 system's simulations, the efficaciously learned structure recovers the dynamical equations. To the best of our knowledge, Informative Ensemble Kalman Learning is new. Results suggest that this approach to optimized Learning is promising.
arXiv commentten pages; accepted for presentation in DDDAS-2020
References in corpus (6)
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Opening the Black Box of Deep Neural Networks via Information
- Kalman-based Stochastic Gradient Method with Stop Condition and Insensitivity to Conditioning
- Fast Ensemble Smoothing
- Adaptive Digital PID Control of a Quadcopter with Unknown Dynamics
- Neural Integration of Continuous Dynamics