Uncovering the Computational Roles of Nonlinearity in Sequence Modeling Using Almost-Linear RNNs

Documenti analoghi

• Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
  di: Brenner, Manuel, et al.
  Pubblicazione: (2024)
• Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
  di: Brenner, Manuel, et al.
  Pubblicazione: (2024)
• Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics
  di: Brenner, Manuel, et al.
  Pubblicazione: (2022)
• Multiple Descents in Deep Learning as a Sequence of Order-Chaos Transitions
  di: Wei, Wenbo, et al.
  Pubblicazione: (2025)
• Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction
  di: Hemmer, Christoph Jürgen, et al.
  Pubblicazione: (2024)