Chen and colleagues: neural ordinary differential equations

What changed

Network depth could be treated as a continuous integration variable in trainable models.

Scientific scope

Exact four-author 2018 paper; earlier ODE mathematics and later augmented neural ODEs separate.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact 2018 NeurIPS paper. Classical ODE solvers, residual networks, later augmented neural ODEs and claims about universal superiority or physical discovery remain separate.

Contributors

• Ricky T. Q. Chen · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Yulia Rubanova · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Jesse Bettencourt · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• David K. Duvenaud · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• NeurIPS, Neural Ordinary Differential Equations
• Chen et al., Neural Ordinary Differential Equations preprint

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction