БЛОГ

Nov 15, 2022

Closed-form continuous-time neural networks

Posted by in categories: information science, robotics/AI

Physical dynamical processes can be modelled with differential equations that may be solved with numerical approaches, but this is computationally costly as the processes grow in complexity. In a new approach, dynamical processes are modelled with closed-form continuous-depth artificial neural networks. Improved efficiency in training and inference is demonstrated on various sequence modelling tasks including human action recognition and steering in autonomous driving.

Comments are closed.