Approximation capability of two hidden layer feedforward neural networks with fixed weights
Neural and Evolutionary Computing
2021-01-25 v1 Information Theory
Numerical Analysis
math.IT
Numerical Analysis
Abstract
We algorithmically construct a two hidden layer feedforward neural network (TLFN) model with the weights fixed as the unit coordinate vectors of the -dimensional Euclidean space and having number of hidden neurons in total, which can approximate any continuous -variable function with an arbitrary precision. This result, in particular, shows an advantage of the TLFN model over the single hidden layer feedforward neural network (SLFN) model, since SLFNs with fixed weights do not have the capability of approximating multivariate functions.
Keywords
Cite
@article{arxiv.2101.09181,
title = {Approximation capability of two hidden layer feedforward neural networks with fixed weights},
author = {Namig J. Guliyev and Vugar E. Ismailov},
journal= {arXiv preprint arXiv:2101.09181},
year = {2021}
}
Comments
13 pages, 3 figures; this article uses the algorithm from arXiv:1708.06219; for associated SageMath worksheet, see https://sites.google.com/site/njguliyev/papers/tlfn