What Do We Understand About Convolutional Networks?
It synthesizes existing knowledge on convolutional networks for researchers, but is incremental as it reviews rather than introduces new methods.
The paper reviews prominent multilayer convolutional architectures, discussing design decisions based on biological and theoretical foundations, and examines attempts to understand ConvNets through visualizations and empirical studies to clarify layer roles and highlight open problems.
This document will review the most prominent proposals using multilayer convolutional architectures. Importantly, the various components of a typical convolutional network will be discussed through a review of different approaches that base their design decisions on biological findings and/or sound theoretical bases. In addition, the different attempts at understanding ConvNets via visualizations and empirical studies will be reviewed. The ultimate goal is to shed light on the role of each layer of processing involved in a ConvNet architecture, distill what we currently understand about ConvNets and highlight critical open problems.