Retracing Hodgkin and Huxley: State Recovery Does Not Certify Mechanism
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/factnn/hh-self-discovery
Sources
- Beyond Predictions in Neural ODEs: Identification and Interventions
- Learning Dynamical Systems from Partial Observations
- Learning Hybrid Biophysical Neuron Models with Neural ODEs
- Geometric regularization of autoencoders via observed stochastic dynamics
- Discovery of the Hidden State in Ionic Models Using a Domain-Specific Recurrent Neural Network
- Deep Kalman Filters
- Universal Differential Equations for Scientific Machine Learning
- On the Identifiability of Controlled World Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks