Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction
Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University(海德堡大学曼海姆医学院中央精神卫生研究所);Heidelberg University(海德堡大学);Interdisciplinary Center for Scientific Computing, Heidelberg University(海德堡大学跨学科科学计算中心)
Christoph Jürgen Hemmer, Manuel Brenner, Florian Hess, Daniel Durstewitz
In dynamical systems reconstruction (DSR) we seek to infer from time series measurements a generative model of the underlying dynamical process. This is a prime objective in any scientific discipline, where we are particularly interested in parsimonious models with a low parameter load. A common strategy here is parameter pruning, removing all parameters with small weights. However, here we find this strategy does not work for DSR, where even low magnitude parameters can contribute considerably to the system dynamics. On the other hand, it is well known that many natural systems which generate complex dynamics, like the brain or ecological networks, have a sparse topology with comparatively few links. Inspired by this, we show that geometric pruning, where in contrast to magnitude-based pruning weights with a low contribution to an attractor's geometrical structure are removed, indeed manages to reduce parameter load substantially without significantly hampering DSR quality. We further find that the networks resulting from geometric pruning have a specific type of topology, and that this topology, and not the magnitude of weights, is what is most crucial to performance. We provide an algorithm that automatically generates such topologies which can be used as priors for generative modeling of dynamical systems by RNNs, and compare it to other well studied topologies like small-world or scale-free networks.
Holographic image reconstruction with phase recovery and autofocusing using recurrent neural networks
University of California, Los Angeles(加利福尼亚大学洛杉矶分校);California Nano Systems Institute (CNSI)(加州纳米系统研究所);David Geffen School of Medicine, University of California, Los Angeles(加利福尼亚大学洛杉矶分校大卫·格芬医学院)
Predictive Process Model Monitoring using Recurrent Neural Networks
KU Leuven(鲁汶大学)
预测性流程监控领域关注案例级模型,以预测单个特定结果,例如特定目标、(剩余)时间或下一个活动/剩余序列。最近,一个更长的地平线,模型范围内的方法已被提出的过程模型预测的形式,它预测整个过程模型的未来状态,通过预测的所有活动,活动的关系,一次使用时间序列预测。本文介绍了\emph{predictive process model monitoring}的概念,它位于预测过程监控和过程模型预测的中间。具体地,通过将过程模型建模为随时间推移存在于活动之间的一组约束,与过程模型预测相比,我们可以捕获活动之间的更详细的信息,同时与通常以与这些约束相同的语言表示的典型预测过程监控目标兼容。为了实现这一点,引入了电影处理(PAM),即,一种能够联合挖掘和预测流程执行的各个窗口中的活动之间的声明性流程约束的新技术。PAM预测什么声明性规则适用于跟踪(基于对象),这也支持将所有约束作为一个流程模型(基于模型)一起预测。各种递归神经网络拓扑结构的灵感来自视频分析定制的时间高维输入的过程模型的演变与窗口作为时间步长,包括编码器-解码器长短期记忆网络,和卷积长短期记忆网络。在实际事件日志中获得的结果表明,这些拓扑结构在预测准确性和精度方面是有效的。
Cine cardiac MRI reconstruction using a convolutional recurrent network with refinement
Institute for Digital Communications, University of Edinburgh(爱丁堡大学数字通信研究所);Institute of Information Science and Technologies “Alessandro Faedo”, National Research Council of Italy (CNR)(意大利国家研究委员会信息科学与技术研究所(亚历山德罗·法埃多));Department of Information Engineering, University of Pisa(比萨大学信息工程系);Institute for Infrastructure and Environment, University of Edinburgh(爱丁堡大学基础设施与环境研究所);The Alan Turing Institute(阿兰·图灵研究所)
Bridging the Gap between Probabilistic and Deterministic Models: A Simulation Study on a Variational Bayes Predictive Coding Recurrent Neural Network Model
KAIST(韩国科学技术院);Okinawa Institute of Science and Technology(冲绳科学技术大学院大学)
Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction
Amsterdam UMC(阿姆斯特丹大学医学中心);University of Amsterdam(阿姆斯特丹大学);MS Center Amsterdam(阿姆斯特丹多发性硬化中心);Amsterdam Neuroscience(阿姆斯特丹神经科学研究所);Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);Leiden University(莱顿大学);Delft University of Technology(代尔夫特理工大学)
Self-supervised Recurrent Neural Network for 4D Abdominal and In-utero MR Imaging
School of Biomedical Engineering and Imaging Sciences, King’s College London(伦敦国王学院生物医学工程与成像科学学院);Department of Women and Children’s Health, School of Life Course Sciences, King’s College London(伦敦国王学院生命历程科学学院妇幼健康系)
Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks
Univ. Bordeaux, CNRS, Bordeaux INP, I2M, UMR 5295(波尔多大学、国家科学研究中心、波尔多工业学院、I2M、UMR 5295);Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800(波尔多大学、国家科学研究中心、波尔多工业学院、LaBRI、UMR 5800);Institute of Mechanics and Fluid Dynamics, TU Bergakademie Freiberg(力学与流体动力学研究所、弗赖堡技术大学);Univ. Grenoble Alpes, CNRS, UMR 5525(格勒诺布尔阿尔卑斯大学、国家科学研究中心、UMR 5525);Arts et Metiers Institute of Technology, CNRS, Bordeaux INP, I2M, UMR 5295(艺术与工艺技术学院、国家科学研究中心、波尔多工业学院、I2M、UMR 5295)
Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction
Dept. of Theoretical Neuroscience, Central Institute of Mental Health, Mannheim, Germany(理论神经科学系,心理健康中央研究所,曼海姆,德国);Faculty of Physics and Astronomy, Heidelberg University, Germany(物理与天文学院,海德堡大学,德国);Faculty of Mathematics and Computer Science, Heidelberg University, Germany(数学与计算机科学学院,海德堡大学,德国);Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Germany(跨学科科学计算中心(IWR),海德堡大学,德国)
University of Stuttgart(斯图加特大学);IIE, Chinese Academy of Sciences(中国科学院信息工程研究所);Imperial College London(帝国理工学院);Griffith University(格里菲斯大学);AMSS, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);University of Southampton(南安普顿大学)