Approximating velocity fields with planted attractors via Neural-ODEs for classification purposes
For machine learning practitioners, this offers a novel dynamical systems approach to classification, but the lack of concrete results suggests incremental progress.
Neural ODEs with planted attractors were used for classification, where attractors represent target classes and the velocity field shapes basins of attraction to direct inputs to correct classes. The method achieved successful classification, though no specific numbers are provided.
In this work, Neural ODEs equipped with a curated collection of equilibrium points have been successfully employed for classification tasks.The planted attractors serve as indicators for the target classes, while the velocity field leveraging the universal approximation capabilities of the architecture shapes the dynamical landscape.This process defines the basins of attraction of the trained model, effectively directing each input provided as an initial condition toward its corresponding destination target.