MLPs to Find Extrema of Functionals

07/01/2020
by   Tao Liu, et al.
0

Multilayer perceptron (MLP) is a class of networks composed of multiple layers of perceptrons, and it is essentially a mathematical function. Based on MLP, we develop a new numerical method to find the extrema of functionals. As demonstrations, we present our solutions in three physic scenes. Ideally, the same method is applicable to any cases where the objective curve/surface can be fitted by second-order differentiable functions. This method can also be extended to cases where there are a finite number of non-differentiable (but continuous) points/surfaces.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/10/2021

Differentiable Surface Rendering via Non-Differentiable Sampling

We present a method for differentiable rendering of 3D surfaces that sup...
research
02/24/2023

Linearization Algorithms for Fully Composite Optimization

In this paper, we study first-order algorithms for solving fully composi...
research
07/15/2020

λ_S: Computable semantics for differentiable programming with higher-order functions and datatypes

Deep learning is moving towards increasingly sophisticated optimization ...
research
01/11/2023

Rig Inversion by Training a Differentiable Rig Function

Rig inversion is the problem of creating a method that can find the rig ...
research
09/22/2021

Differentiable Surface Triangulation

Triangle meshes remain the most popular data representation for surface ...

Please sign up or login with your details

Forgot password? Click here to reset