Exact Fixed-Point Constraints in Neural-ODEs: Injecting Prior Knowledge into the Network Parameters
cond-mat.dis-nn, cs.LG, physics.bio-ph
Submitted: 2026-05-11
Updated: 2026-11-12
Terminology
Sources
- Neural Ordinary Differential Equations
- Universal Approximation Property of Neural Ordinary Differential Equations
- HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees
- Approximation and interpolation of deep neural networks
- Projected Neural Differential Equations for Learning Constrained Dynamics
- Adam: A Method for Stochastic Optimization
Related papers
- Topological metal-insulator transitions in one-dimensional non-Hermitian quasicrystals: beyond PT-symmetry
- Microscopic and collective signatures of feature learning in neural networks
- Synchronous and asynchronous Monte Carlo dynamics of mean-field spin glasses with rotationally invariant couplings: what they share and where they differ
- Reentrant Localization Length in a Quasiperiodic Thue-Morse Chain
- Beyond Ground States: Learning Many-Body Hamiltonians for p-Bit Invertible Arithmetic
- Linear equivalence of nonlinear recurrent neural networks