An Effective Gram Matrix Characterizes Generalization in Deep Networks

Documenti analoghi

• The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
  di: Mao, Jialin, et al.
  Pubblicazione: (2023)
• Prospective Learning: Learning for a Dynamic Future
  di: De Silva, Ashwin, et al.
  Pubblicazione: (2024)
• An Information-Geometric Distance on the Space of Tasks
  di: Gao, Yansong, et al.
  Pubblicazione: (2020)
• Model Zoo: A Growing "Brain" That Learns Continually
  di: Ramesh, Rahul, et al.
  Pubblicazione: (2021)
• Learning Capacity: A Measure of the Effective Dimensionality of a Model
  di: Chen, Daiwei, et al.
  Pubblicazione: (2023)