Feedforward neural nets as discretization schemes for ODEs and DAEs (Q1372058)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Feedforward neural nets as discretization schemes for ODEs and DAEs |
scientific article |
Statements
Feedforward neural nets as discretization schemes for ODEs and DAEs (English)
0 references
18 June 1998
0 references
Because of their neurophysical origin neural nets can be studied for classification tasks, approximation properties or iterative algorithms. They can be interpreted as a distributed or massively parallel computer, where each unit accumulates a scalar product and computes a one-dimensional nonlinear activation function. A supervised learning strategy defines a nonlinear least squares problem, which is solved by gradient techniques such as backpropagation. Interpreting the weights in a net as state variable feedforward neural nets can be designed as numerical discretization schemes for ordinary differential equations (ODEs) and differential-algebraic equations (DAEs). The net architecture for the implicit Euler scheme is presented here and some experiments are given. The net approach is of interest for the overdetermined index-3 approach of DAEs from multibody system dynamics. More generally, these nets determine a parallel shooting-type algorithm.
0 references
parallel computation
0 references
neural nets
0 references
iterative algorithms
0 references
learning strategy
0 references
nonlinear least squares problem
0 references
feedforward neural nets
0 references
index-3
0 references
multibody system dynamics
0 references
parallel shooting-type algorithm
0 references