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.
State, global and local parameter estimation using local ensemble Kalman filters: applications to online machine learning of chaotic dynamics
CEREA(大气环境教学与研究中心);École des Ponts(巴黎桥路学院);EDF R&D(法国电力集团研发中心);LMD/IPSL(动力气象学实验室/皮埃尔-西蒙·拉普拉斯研究所);ENS(巴黎高等师范学院);PSL Université(巴黎文理研究大学);École Polytechnique(巴黎综合理工学院);Institut Polytechnique de Paris(巴黎理工学院);Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心)
U-Net Kalman Filter (UNetKF): An Example of Machine Learning-assisted Ensemble Data Assimilation
University Cooperation of Atmospheric Research(大学大气研究合作组织);National Oceanic and Atmospheric Administration/Geophysical Fluid Dynamics Laboratory(美国国家海洋和大气管理局/地球物理流体动力学实验室);Princeton University(普林斯顿大学)