Solving complex differential equation using unsupervised neural networks

Authors

  • Christopher P. Monterola ⋅ PH National Institute of Physics, University of the Philippines Diliman
  • Caesar A. Saloma ⋅ PH National Institute of Physics, University of the Philippines Diliman

Abstract

The ability of neural networks (NN) to solve differential equations (DE) was demonstrated recently. In this paper, we demonstrate a general method of solving complex differential equation based on unsupervised neural networks. In particular, the paradigm is utilized to approximate the temporal profile of pulse propagating along a nonlinear and dispersive medium.

Downloads

Issue

Article ID

SPP-1998-IC-02

Section

Instrumentation and Computational Physics

Published

1998-10-27

How to Cite

[1]
CP Monterola and CA Saloma, Solving complex differential equation using unsupervised neural networks, Proceedings of the Samahang Pisika ng Pilipinas 16, SPP-1998-IC-02 (1998). URL: https://proceedings.spp-online.org/article/view/SPP-1998-IC-02.