Neural Networks are Integrable

2023/10/22 by Liu, Yucong · 1 citation
#FOS: Mathematics #Numerical Analysis (math.NA)

paper · doi:10.48550/arxiv.2310.14394

Abstract

In this study, we explore the integration of Neural Networks, a powerful class of functions known for their exceptional approximation capabilities. Our primary emphasis is on the integration of multi-layer Neural Networks, a challenging task within this domain. To tackle this challenge, we introduce a novel numerical method that consist of a forward algorithm and a corrective procedure. Our experimental results demonstrate the accuracy achieved through our integration approach.

Cited by

• Geometric Integration for Neural Control Variates

Related

• Fixed Integral Neural Networks
• Neural Network Processing Neural Networks: An efficient way to learn higher order functions
• Neural Integration of Continuous Dynamics
• Structured and Balanced Multi-Component and Multi-Layer Neural Networks
• A three layer neural network can represent any multivariate function