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 2308.02599cs.LGcs.NAeess.SPmath.NA
收藏

分支潜神经映射(Branched Latent Neural Maps)

Branched Latent Neural Maps

Stanford University(斯坦福大学)

Matteo Salvador, Alison Lesley Marsden

AI总结:

本研究提出分支潜神经映射(BLNM),通过部分连接神经网络结构解耦不同作用输入,以小数据量、短训练时间实现优异泛化,在心脏电生理模拟中实现5000倍加速,可快速求解逆问题。

摘要:

我们提出分支潜神经映射(Branched Latent Neural Maps,BLNMs),用于学习编码复杂物理过程的有限维输入-输出映射。BLNM由一种简洁紧凑的前馈部分连接神经网络定义,该网络在结构上解耦具有不同内在作用的输入(例如微分方程的时间变量与模型参数),同时将它们转换为通用目标场。BLNM利用潜输出增强所学习的动力学特性,并通过在小训练数据集、单处理器短训练时间下展现出的优异泛化性能打破维度灾难。实际上,无论测试阶段采用何种离散化方式,其泛化误差都保持在相当水平。此外,部分连接结构显著减少了可调参数的数量。我们在一项具有挑战性的测试案例中展示了BLNM的能力,该案例涉及左心发育不良综合征儿科患者的双心室心脏模型电生理模拟。该模型包含用于快速传导的一维Purkinje网络和三维心脏-躯干几何结构。具体而言,我们在150条计算机生成的12导联心电图(electrocardiograms, ECGs)上训练BLNM,这些心电图覆盖了细胞尺度和器官层面的7个模型参数。尽管12导联ECG呈现出带有陡峭梯度的极快动力学特性,但经过自动超参数调优后,最优BLNM仅包含7个隐藏层、每层19个神经元,且在单个CPU上训练耗时不到3小时。在包含50次电生理模拟的测试数据集上,所得均方误差约为$10^{-4}$。在在线阶段,BLNM可在标准计算机的单核上实现心脏电生理实时模拟,速度提升5000倍,并且可通过全局优化在几秒的计算时间内用于求解逆问题。

英文摘要:

We introduce Branched Latent Neural Maps (BLNMs) to learn finite dimensional input-output maps encoding complex physical processes. A BLNM is defined by a simple and compact feedforward partially-connected neural network that structurally disentangles inputs with different intrinsic roles, such as the time variable from model parameters of a differential equation, while transferring them into a generic field of interest. BLNMs leverage latent outputs to enhance the learned dynamics and break the curse of dimensionality by showing excellent generalization properties with small training datasets and short training times on a single processor. Indeed, their generalization error remains comparable regardless of the adopted discretization during the testing phase. Moreover, the partial connections significantly reduce the number of tunable parameters. We show the capabilities of BLNMs in a challenging test case involving electrophysiology simulations in a biventricular cardiac model of a pediatric patient with hypoplastic left heart syndrome. The model includes a 1D Purkinje network for fast conduction and a 3D heart-torso geometry. Specifically, we trained BLNMs on 150 in silico generated 12-lead electrocardiograms (ECGs) while spanning 7 model parameters, covering cell-scale and organ-level. Although the 12-lead ECGs manifest very fast dynamics with sharp gradients, after automatic hyperparameter tuning the optimal BLNM, trained in less than 3 hours on a single CPU, retains just 7 hidden layers and 19 neurons per layer. The resulting mean square error is on the order of $10^{-4}$ on a test dataset comprised of 50 electrophysiology simulations. In the online phase, the BLNM allows for 5000x faster real-time simulations of cardiac electrophysiology on a single core standard computer and can be used to solve inverse problems via global optimization in a few seconds of computational 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。

↑