Can I read Forward and Inverse Approximation Theory for Linear Temporal Convolutional Networks on EtoBox?

Forward and Inverse Approximation Theory for Linear Temporal Convolutional Networks by Jiang, Haotian; Li, Qianxiao is a scholarly article available to read on EtoBox.

What is Forward and Inverse Approximation Theory for Linear Temporal Convolutional Networks about?

We present a theoretical analysis of the approximation properties of convolutional architectures when applied to the modeling of temporal sequences. Specifically, we prove an approximation rate estimate (Jackson-type result) and an inverse approximation theorem (Bernstein-type result), which together provide a comprehensive characterization of the types of sequential relationships that can be efficiently captured by a temporal convolutional architecture. The rate estimate improves upon a previous result via the introduction of a refined complexity measure, whereas the inverse approximation theorem is new.

Author

Jiang, Haotian; Li, Qianxiao

Published

2023

Language

EN