PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Units

DOI10.4208/jms.v53n2.20.03zbMath1463.41013arXiv1909.05136OpenAlexW3022969236MaRDI QIDQ5127796

Bo Li, Hai-jun Yu, Shanshan Tang

Publication date: 27 October 2020

Published in: Journal of Mathematical Study (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1909.05136

zbMATH Keywords

sparse griddeep neural networkrectified linear unitrectified power unit

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Approximation by polynomials (41A10) Approximation by other special function classes (41A30)

Related Items (3)

De Rham compatible deep neural network FEM ⋮ Deep Learning in High Dimension: Neural Network Expression Rates for Analytic Functions in \(\pmb{L^2(\mathbb{R}^d,\gamma_d)}\) ⋮ Better Approximations of High Dimensional Smooth Functions by Deep Neural Networks with Rectified Power Units

This page was built for publication: PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Units