Beyond topography: Topographic regularization improves robustness and reshapes representations in convolutional neural networks

Documenti analoghi

• Explaining Human Comparisons using Alignment-Importance Heatmaps
  di: Truong, Nhut, et al.
  Pubblicazione: (2024)
• Dynamical loss functions shape landscape topography and improve learning in artificial neural networks
  di: Pallero, Eduardo Lavin, et al.
  Pubblicazione: (2024)
• Symplectic convolutional neural networks
  di: Yıldız, Süleyman, et al.
  Pubblicazione: (2025)
• Theory of periodic convolutional neural network
  di: Liu, Yuqing
  Pubblicazione: (2025)
• Adversarially robust generalization theory via Jacobian regularization for deep neural networks
  di: Wu, Dongya, et al.
  Pubblicazione: (2024)