The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks

Documenti analoghi

• ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized Experiments
  di: Cha, Taehun, et al.
  Pubblicazione: (2024)
• Toward universal steering and monitoring of AI models
  di: Beaglehole, Daniel, et al.
  Pubblicazione: (2025)
• xRFM: Accurate, scalable, and interpretable feature learning models for tabular data
  di: Beaglehole, Daniel, et al.
  Pubblicazione: (2025)
• OPC: One-Point-Contraction Unlearning Toward Deep Feature Forgetting
  di: Jung, Jaeheun, et al.
  Pubblicazione: (2025)
• Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
  di: Beaglehole, Daniel, et al.
  Pubblicazione: (2024)