Please use this identifier to cite or link to this item:
Title: Physics-informed neural networks with non-differentiable loss
Authors: Yang, Junyan
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Yang, J. (2022). Physics-informed neural networks with non-differentiable loss. Final Year Project (FYP), Nanyang Technological University, Singapore.
Project: B1099-211
Abstract: Physics-informed Neural Networks (PINN) are special neural networks that are designed for scientific computing tasks. Recent research has found its promising capability to integrate any given law of physics in different forms including general nonlinear partial differentiable equations. It has shown great potential to function as a data-efficient universal function approximator that is able to encode any underlying physical laws as prior information. However, just like other ordinary neural networks, the usage of such knowledge still relies on the optimization of neural networks which implies that a differentiable loss function is indispensable. Yet sometimes human knowledge contradict such requirement and knowledge, such as qualitative conclusions, can not be constructed into PINN directly. After a delicate literature review, the surrogate model was chosen as a better fit to substitute the original loss function, which can reconstruct a continuous and differentiable function from samples from the original function. We then propose the PINN with surrogate loss (SL-PINN). It greatly boosts the performance when integrating human knowledge into the neural network
Schools: School of Electrical and Electronic Engineering 
Organisations: A*STAR Institute of High Performance Computing
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
FYP report2.27 MBAdobe PDFView/Open

Page view(s)

Updated on Apr 11, 2024


Updated on Apr 11, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.