Search Results for author:
Found 7 papers, 1 papers with code
Interpolation, Approximation and Controllability of Deep Neural Networks
We investigate the expressive power of deep residual neural networks idealized as continuous dynamical systems through control theory.
Computational Optics for Mobile Terminals in Mass Production
Correcting the optical aberrations and the manufacturing deviations of cameras is a challenging task.
On the Universal Approximation Property of Deep Fully Convolutional Neural Networks
We study the approximation of shift-invariant or equivariant functions by deep fully convolutional networks from the dynamical systems perspective.
Deep Neural Network Approximation of Invariant Functions through Dynamical Systems
We study the approximation of functions which are invariant with respect to certain permutations of the input indices using flow maps of dynamical systems.
Non-blind optical degradation correction via frequency self-adaptive and finetune tactics
In mobile photography applications, limited volume constraints the diversity of optical design.
Aspect-based Sentiment Analysis through EDU-level Attentions
A sentence may express sentiments on multiple aspects.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Deep Learning via Dynamical Systems: An Approximation Perspective
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.
