paper-with-me

Papers

Quantitative approximation results for complex-valued neural networks

2021-02-25 · A. Caragea, D. G. Lee, J. Maly, G. Pfander, F. Voigtlaender

Until recently, applications of neural networks in machine learning have almost exclusively relied on real-valued networks. It was recently observed, however, that complex-valued neural networks (CVNNs) exhibit superior performance in applications in which the input is naturally complex-valued, such as MRI fingerprinting. While the mathematical theory of real-valued networks has, by now, reached some level of maturity, this is far from true for complex-valued networks. In this paper, we analyze the expressivity of complex-valued networks by providing explicit quantitative error bounds for approximating $C^n$ functions on compact subsets of $\mathbb{C}^d$ by complex-valued neural networks that employ the modReLU activation function, given by $\sigma(z) = \mathrm{ReLU}(|z| - 1) \, \mathrm{sgn} (z)$, which is one of the most popular complex activation functions used in practice. We show that the derived approximation rates are optimal (up to log factors) in the class of modReLU networks with weights of moderate growth.

📄 PDF Abstract BibTeX arXiv:2102.13092

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

modReLU modReLU is an activation that is a modification of a ReLU. It is a pointwise nonlinearity, $\sigma\_{modReLU}\left(z\right) : C…

Similar Papers 제목 키워드 기반

Optimal approximation using complex-valued neural networks

2023-03-29 · NeurIPS 2023 11

Complex-valued neural networks (CVNNs) have recently shown promising empirical success, for instance for increasing the stability of recurrent neural networks and for improving the performance in tasks with complex-value…

Algebraic function based Banach space valued ordinary and fractional neural network approximations

2022-02-11 · George A Anastassiou

Here we research the univariate quantitative approximation, ordinary and fractional, of Banach space valued continuous functions on a compact interval or all the real line by quasi-interpolation Banach space valued neura…

Universal Approximation Theorem for Vector- and Hypercomplex-Valued Neural Networks

2024-01-04 · Marcos Eduardo Valle, Wington L. Vital, Guilherme Vieira

The universal approximation theorem states that a neural network with one hidden layer can approximate continuous functions on compact sets with any desired precision. This theorem supports using neural networks for vari…

valid

Extending the Universal Approximation Theorem for a Broad Class of Hypercomplex-Valued Neural Networks

2022-09-06 · Wington L. Vital, Guilherme Vieira, Marcos Eduardo Valle

The universal approximation theorem asserts that a single hidden layer neural network approximates continuous functions with any desired precision on compact sets. As an existential result, the universal approximation th…

regression

Universal approximation with complex-valued deep narrow neural networks

2023-05-26 · Paul Geuchen, Thomas Jahn, Hannes Matt

We study the universality of complex-valued neural networks with bounded widths and arbitrary depths. Under mild assumptions, we give a full description of those activation functions $\varrho:\mathbb{C}\to \mathbb{C}$ th…