activity
20222026
most citedHomotopy-based training of NeuralODEs for accurate dynamics discovery

2 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2023

Moderate Adaptive Linear Units (MoLU)

Hankyul Koh, Joon-hyuk Ko, Wonho Jhe

We propose the Moderate Adaptive Linear Unit (MoLU), a novel activation function for deep neural networks, defined analytically as: f(x)=x \times (1+tanh(x))/2. MoLU combines mathe…

cs.LG2022★ 2 cited

Homotopy-based training of NeuralODEs for accurate dynamics discovery

Joon-Hyuk Ko, Hankyul Koh, Nojun Park +1

Neural Ordinary Differential Equations (NeuralODEs) present an attractive way to extract dynamical laws from time series data, as they bridge neural networks with the differential…