Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks

Documenti analoghi

• Deep Network Approximation: Beyond ReLU to Diverse Activation Functions
  di: Zhang, Shijun, et al.
  Pubblicazione: (2023)
• How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?
  di: Lai, Kuo-Wei, et al.
  Pubblicazione: (2026)
• Random ReLU Neural Networks as Non-Gaussian Processes
  di: Parhi, Rahul, et al.
  Pubblicazione: (2024)
• Neural Tangent Kernels and Fisher Information Matrices for Simple ReLU Networks with Random Hidden Weights
  di: Takeuchi, Jun'ichi, et al.
  Pubblicazione: (2025)
• Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks
  di: Chen, Wenlin, et al.
  Pubblicazione: (2023)