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 1802.03497cs.LGstat.ML
收藏

用深度生成神经网络从局部快照建模全局动态

Modeling Global Dynamics from Local Snapshots with Deep Generative Neural Networks

Yale University(耶鲁大学);Utah State University(犹他州立大学);Princeton University(普林斯顿大学);Université de Montréal(蒙特利尔大学)

Scott Gigante, David van Dijk, Kevin Moon, Alexander Strzalkowski, Guy Wolf, Smita Krishnaswamy

摘要:

复杂高维随机动力系统在自然科学特别是生物学中有着广泛的应用。然而,虽然这些系统很难分析描述,“快照”测量采样系统的输出往往是可用的。为了对给定快照数据或局部转换的此类系统的动态进行建模,我们提出了一个深度神经网络框架,我们称之为动态建模网络或DyMoN。DyMoN是一个神经网络框架,被训练为深度生成马尔可夫模型,其下一个状态是基于当前状态的概率分布。DyMoN使用当前和下一状态对的样本进行训练,因此不需要纵向测量。我们展示了DyMoN在浅层模型(如卡尔曼滤波器和隐马尔可夫模型)和其他深层模型(如递归神经网络)中体现动态(可以通过神经网络的扰动进行研究)并生成纵向假设轨迹的能力的优势。我们进行了三个案例研究,在这些案例中,我们将DyMoN应用于不同类型的生物系统,并通过检查学习模型来提取每种情况下的动态特征。

英文摘要:

Complex high dimensional stochastic dynamic systems arise in many applications in the natural sciences and especially biology. However, while these systems are difficult to describe analytically, "snapshot" measurements that sample the output of the system are often available. In order to model the dynamics of such systems given snapshot data, or local transitions, we present a deep neural network framework we call Dynamics Modeling Network or DyMoN. DyMoN is a neural network framework trained as a deep generative Markov model whose next state is a probability distribution based on the current state. DyMoN is trained using samples of current and next-state pairs, and thus does not require longitudinal measurements. We show the advantage of DyMoN over shallow models such as Kalman filters and hidden Markov models, and other deep models such as recurrent neural networks in its ability to embody the dynamics (which can be studied via perturbation of the neural network) and generate longitudinal hypothetical trajectories. We perform three case studies in which we apply DyMoN to different types of biological systems and extract features of the dynamics in each case by examining the learned model.

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。

↑