Reinitializing weights vs units for maintaining plasticity in neural networks

Documenti analoghi

• Experiment on creating a neural network with weights determined by the potential of a simulated electrostatic field
  di: Polad, Geidarov
  Pubblicazione: (2025)
• Training neural networks without backpropagation using particles
  di: Kumar, Deepak
  Pubblicazione: (2024)
• DYNAP-SE2: a scalable multi-core dynamic neuromorphic asynchronous spiking neural network processor
  di: Richter, Ole, et al.
  Pubblicazione: (2023)
• Runtime Analysis of Evolutionary Diversity Optimization on the Multi-objective (LeadingOnes, TrailingZeros) Problem
  di: Antipov, Denis, et al.
  Pubblicazione: (2024)
• Reconsidering the energy efficiency of spiking neural networks
  di: Yan, Zhanglu, et al.
  Pubblicazione: (2024)