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 1710.01693cs.LGphysics.comp-phphysics.data-an
收藏

基于深度学习的噪声混沌时间序列无模型预测

Model-free prediction of noisy chaotic time series by deep learning

IBM T.J. Watson Research Center(IBM T.J. Watson 研究中心)

Kyongmin Yeo

摘要:

我们提出了一个深度神经网络的无模型预测的混沌动力系统从嘈杂的意见。所提出的深度学习模型旨在预测状态变量的条件概率分布。采用长短期记忆网络(LSTM)对非线性动力学进行建模,并使用softmax层来近似概率分布。LSTM模型通过最小化正则化交叉熵函数来训练。LSTM模型针对延迟时间混沌动力系统、Mackey-Glass和Ikeda方程进行了验证。结果表明,目前的LSTM通过有效地过滤掉噪声,对非线性动力学进行了很好的预测。研究发现,LSTM模型的多步预测的预测不确定性不是时间的单调函数;预测的标准差可能会随时间动态增加或减少。

英文摘要:

We present a deep neural network for a model-free prediction of a chaotic dynamical system from noisy observations. The proposed deep learning model aims to predict the conditional probability distribution of a state variable. The Long Short-Term Memory network (LSTM) is employed to model the nonlinear dynamics and a softmax layer is used to approximate a probability distribution. The LSTM model is trained by minimizing a regularized cross-entropy function. The LSTM model is validated against delay-time chaotic dynamical systems, Mackey-Glass and Ikeda equations. It is shown that the present LSTM makes a good prediction of the nonlinear dynamics by effectively filtering out the noise. It is found that the prediction uncertainty of a multiple-step forecast of the LSTM model is not a monotonic function of time; the predicted standard deviation may increase or decrease dynamically in time.

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。

↑