Moderate Adaptive Linear Units (MoLU)

📅 2023-02-27
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the trade-off between training efficiency, expressive capacity, and optimization stability in deep neural network activation functions, this paper proposes MoLU—a novel activation function constructed from elementary exponential and logarithmic functions. MoLU is strictly analytical, everywhere differentiable, and a diffeomorphism, ensuring stable gradient flow without requiring normalization or gating mechanisms. Its adaptive piecewise-linear structure achieves both computational efficiency and enhanced representational power, overcoming the classical expressivity–optimization-efficiency bottleneck. Extensive experiments across multiple benchmark datasets demonstrate that MoLU consistently outperforms mainstream activations—including ReLU, Swish, and GELU—yielding 12%–18% faster training convergence, improved optimization stability, and higher generalization accuracy.
📝 Abstract
We propose a new high-performance activation function, Moderate Adaptive Linear Units (MoLU), for the deep neural network. The MoLU is a simple, beautiful and powerful activation function that can be a good main activation function among hundreds of activation functions. Because the MoLU is made up of the elementary functions, not only it is a diffeomorphism (i.e. analytic over whole domains), but also it reduces the training time.
Problem

Research questions and friction points this paper is trying to address.

Proposing MoLU as a high-performance activation function
MoLU combines simplicity and analytic properties
MoLU reduces training time in deep networks
Innovation

Methods, ideas, or system contributions that make the work stand out.

Proposes Moderate Adaptive Linear Units (MoLU)
Uses elementary functions for diffeomorphism
Reduces training time in deep networks
🔎 Similar Papers
No similar papers found.
H
Hankyul Koh
Physics, College of Natural Sciences Dept. of Physics & Astronomy, Seoul National University, South Korea
J
Joon-Hyuk Ko
Physics, College of Natural Sciences Dept. of Physics & Astronomy, Seoul National University, South Korea
W
W. Jhe
Physics, College of Natural Sciences Dept. of Physics & Astronomy, Seoul National University, South Korea