Architectural Scaling Surpass Basis Complexity? Efficient KANs with Single-Parameter Design

Documenti analoghi

• LArctan-SKAN: Simple and Efficient Single-Parameterized Kolmogorov-Arnold Networks using Learnable Trigonometric Function
  di: Chen, Zhijie, et al.
  Pubblicazione: (2024)
• A Novel Two-Phase Cooperative Co-evolution Framework for Large-Scale Global Optimization with Complex Overlapping
  di: Qiu, Wenjie, et al.
  Pubblicazione: (2025)
• Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution
  di: Guo, Hongshu, et al.
  Pubblicazione: (2024)
• Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning
  di: Ma, Zeyuan, et al.
  Pubblicazione: (2024)
• RLEMMO: Evolutionary Multimodal Optimization Assisted By Deep Reinforcement Learning
  di: Lian, Hongqiao, et al.
  Pubblicazione: (2024)