arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.09915cs.LGmath.DSnlin.CDstat.ML
收藏

信息神经网络Enhancement Kalman学习

Informative Neural Ensemble Kalman Learning

Massachusetts Institute of Technology(麻省理工学院)

Margaret Trautner, Gabriel Margolis, Sai Ravela

摘要:

在随机系统中,信息方法选择关键的测量或决策变量,最大限度地提高信息增益,以提高模型相关的推理的功效。神经学习也体现了随机动力学,但信息学习发展较少。在这里,我们提出了信息Energy-Energy-Kalman学习,它用自适应Energy-Kalman滤波器卡尔曼滤波器代替反向传播来量化不确定性,并使学习过程中的信息增益最大化。在标准数据集上展示了Ensemble卡尔曼学习的竞争性能之后,我们将信息方法应用于神经结构学习。特别是,我们表明,当从Lorenz-63系统的模拟训练时,有效学习的结构恢复了动力学方程。据我们所知,信息包络卡尔曼学习是新的。结果表明,这种优化学习的方法是有前途的。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑