Biblio Discovery — Demo Discovery Service

4 hasil

Menampilkan 1–4 · 0,19 detik · RSS

Jurnal

Communications in Computational Physics

Scopus

ISSN 1815-2406 · Cambridge University Press · 4 artikel di indeks

  1. Artikel Jurnal Teks lengkap

    Dying ReLU and Initialization: Theory and Numerical Examples

    Lu Lu; Yeonjong Shin; Yanhui Su dkk.

    Communications in Computational Physics · 2020 · Inggris · OpenAlex Scopus

    The dying ReLU refers to the problem when ReLU neurons become inactive and only output 0 for any input. There are many empirical and heuristic explanations of why ReLU neurons die. However, little is known about its theoretical analysis. In this paper, we rigorously prove that a deep ReLU network…

  2. Artikel Jurnal Teks lengkap

    On the Convergence of Physics Informed Neural Networks for Linear Second-Order Elliptic and Parabolic Type PDEs

    Yeonjong Shin; Jérôme Darbon; George Em Karniadakis

    Communications in Computational Physics · 2020 · Inggris · OpenAlex Scopus

    Physics informed neural networks (PINNs) are deep learning based techniques for solving partial differential equations (PDEs) encountered in computational science and engineering. Guided by data and physical laws, PINNs find a neural network that approximates the solution to a system of PDEs. Such…

  3. Artikel Jurnal Teks lengkap

    Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations

    Ameya D. Jagtap; George Em Karniadakis

    Communications in Computational Physics · 2020 · Inggris · OpenAlex Scopus

    We propose a generalized space-time domain decomposition approach for the physics-informed neural networks (PINNs) to solve nonlinear partial differential equations (PDEs) on arbitrary complex-geometry domains. The proposed framework, named eXtended PINNs (XPINNs), further pushes the boundaries of…

  4. Artikel Jurnal Teks lengkap

    Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks

    Zhi-Qin John Xu Zhi-Qin John Xu; Yaoyu Zhang; Tao Luo dkk.

    Communications in Computational Physics · 2020 · Inggris · OpenAlex Scopus

    We study the training process of Deep Neural Networks (DNNs) from the Fourier analysis perspective. We demonstrate a very universal Frequency Principle (F-Principle) — DNNs often fit target functions from low to high frequencies — on high-dimensional benchmark datasets such as MNIST/CIFAR10 and…