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
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
- Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks (NeurIPS 2025 · similarity 0.86)
- ReLUs Are Sufficient for Learning Implicit Neural Representations (ICML 2024 · similarity 0.85)
- Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics (NeurIPS 2025 · similarity 0.85)
- Activation-Descent Regularization for Input Optimization of ReLU Networks (ICML 2024 · similarity 0.84)
- Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks (NeurIPS 2024 · similarity 0.84)
- From Activation to Initialization: Scaling Insights for Optimizing Neural Fields (CVPR 2024 · similarity 0.84)
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.
