# Deep Learning via Dynamical Systems: An Approximation Perspective

22 Dec 2019Qianxiao LiTing LinZuowei Shen

We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for universal approximation using continuous-time deep residual networks, which can also be understood as approximation theories in $L^p$ using flow maps of dynamical systems... (read more)

PDF Abstract

No code implementations yet. Submit your code now