3 papers
math.NA2026
A Fully Dual Domain Decomposition Method for Extreme Learning Machines Using GenEO Spectral Coarse Spaces
Chang-Ock Lee, Byungeun Ryoo
Extreme learning machines (ELMs) are a class of machine learning algorithms that randomly intialize and subsequently fix the hidden layer parameters, and solve for the last layer c…
math.NA2025
A Neumann-Neumann Acceleration with Coarse Space for Domain Decomposition of Extreme Learning Machines
Chang-Ock Lee, Byungeun Ryoo
Extreme learning machines (ELMs), which preset hidden layer parameters and solve for last layer coefficients via a least squares method, can typically solve partial differential eq…
math.NA2024
A Nonoverlapping Domain Decomposition Method for Extreme Learning Machines: Elliptic Problems
Chang-Ock Lee, Youngkyu Lee, Byungeun Ryoo
Extreme learning machine (ELM) is a methodology for solving partial differential equations (PDEs) using a single hidden layer feed-forward neural network. It presets the weight/bia…