Journal
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
Volume 41, Issue -, Pages 406-413Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.jvcir.2016.11.003
Keywords
Convolutional neural network (CNN); Nonlinear activation; RECOS model; Rectified linear unit (ReLU); MNIST dataset
Funding
- DARPA
- Air Force Research Laboratory (AFRL) [FA8750-16-2-0173]
Ask authors/readers for more resources
This work attempts to address two fundamental questions about the structure of the convolutional neural networks (CNN): (1) why a nonlinear activation function is essential at the filter output of all intermediate layers? (2) what is the advantage of the two-layer cascade system over the one-layer system? A mathematical model called the REctified-COrrelations on a Sphere (RECOS) is proposed to answer these two questions. After the CNN training process, the converged filter weights define a set of anchor vectors in the RECOS model. Anchor vectors represent the frequently occurring patterns (or the spectral components). The necessity of rectification is explained using the RECOS model. Then, the behavior of a two-layer RECOS system is analyzed and compared with its one-layer counterpart. The LeNet-5 and the MNIST dataset are used to illustrate discussion points. Finally, the RECOS model is generalized to a multilayer system with the AlexNet as an example. (C) 2016 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available