Dissecting Neural ODEs
This work addresses interpretability issues in continuous deep learning for researchers and practitioners, but it is incremental as it builds on existing formulations.
The paper tackles the challenge of understanding the inner workings of Neural ODEs, which are used as black-box modules, by analyzing how design choices affect their underlying dynamics.
Continuous deep learning architectures have recently re-emerged as Neural Ordinary Differential Equations (Neural ODEs). This infinite-depth approach theoretically bridges the gap between deep learning and dynamical systems, offering a novel perspective. However, deciphering the inner working of these models is still an open challenge, as most applications apply them as generic black-box modules. In this work we "open the box", further developing the continuous-depth formulation with the aim of clarifying the influence of several design choices on the underlying dynamics.