4 hasil
Menampilkan 1–4 · 0,19 detik · RSS
Communications in Computational Physics
Scopus
ISSN 1815-2406 · Cambridge University Press · 4 artikel di indeks
-
Artikel Jurnal Teks lengkap
Dying ReLU and Initialization: Theory and Numerical Examples
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…
-
Artikel Jurnal Teks lengkap
On the Convergence of Physics Informed Neural Networks for Linear Second-Order Elliptic and Parabolic Type PDEs
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…
-
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
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…
-
Artikel Jurnal Teks lengkap
Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
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…