Understanding Convolutional Neural Networks with A Mathematical Model

  • C.-C. Jay Kuo
  • Published 2016 in J. Visual Communication and Image Representation

Abstract

This work attempts to address two fundamental questions about the structure of the convolutional neural networks (CNN): 1) why a non-linear activation function is essential at the filter output of every convolutional layer? 2) what is the advantage of the two-layer cascade system over the one-layer system? A mathematical model called the “REctified… (More)
DOI: 10.1016/j.jvcir.2016.11.003

Topics

12 Figures and Tables

Slides referencing similar topics