Approximation error of single hidden layer neural networks with fixed weights

2022/02/07 by Ismailov, Vugar · 1 citation
#41A30 #41A63 #68T05 #92B20 #Classical Analysis and ODEs (math.CA) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2202.03289

Abstract

This paper provides an explicit formula for the approximation error of single hidden layer neural networks with two fixed weights.

Cited by

• Best approximation of a three-variable function by sum of one-variable coordinate functions

Related

• On Sharpness of Error Bounds for Single Hidden Layer Feedforward Neural Networks
• Pulling back error to the hidden-node parameter technology: Single-hidden-layer feedforward network without output weight
• Bounds on the Approximation Power of Feedforward Neural Networks
• On Sharpness of Error Bounds for Multivariate Neural Network Approximation
• Approximation power of random neural networks