We investigate the expressive power of deep residual neural networks
ide...
We study the approximation of shift-invariant or equivariant functions b...
We study the approximation of functions which are invariant with respect...
This paper proposes a new neural network architecture by introducing an
...
Discretization invariant learning aims at learning in the
infinite-dimen...
This paper studies the approximation error of ReLU networks in terms of ...
This paper develops simple feed-forward neural networks that achieve the...
This paper concentrates on the approximation power of deep feed-forward
...
A three-hidden-layer neural network with super approximation power is
in...
A new network with super approximation power is introduced. This network...
We present the viewpoint that optimization problems encountered in machi...
This paper establishes optimal approximation error characterization of d...
We build on the dynamical systems approach to deep learning, where deep
...
This paper quantitatively characterizes the approximation power of deep
...
We study the approximation efficiency of function compositions in nonlin...
Despite its empirical success, the theoretical underpinnings of the
stab...
Image restoration is one of the most important areas in imaging science....
Spline wavelet tight frames of Ron-Shen have been used widely in frame b...