AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions

Haoyuan Sun, Zihao Wu, Bo Xia, Pu Chang, Zibin Dong, Yifu Yuan, Yongzhe Chang, Xueqian Wang

ICLR 2025 · Architectures and efficiency › RNNs and normalization · approach: Mechanistic circuit interpretability

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an entropy-based, theory-guided method for searching and optimizing neural network activation functions, rather than relying on empirical trial-and-error.

Problem

Activation function search has relied on empirical knowledge and lacks theoretical guidance, which hinders finding more effective activation functions for ANNs.

Approach

Uses an entropy-based perspective to guide the search and optimization of activation functions, providing theoretical grounding instead of purely empirical search.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy