papers AI Learner
The Github is limit! Click to go to the new site.

Conceptual Content in Deep Convolutional Neural Networks: An analysis into multi-faceted properties of neurons

2019-05-20
Zahra Sadeghi

Abstract

In this paper we analyze convolutional layers of VGG16 model pre-trained on ILSVRC2012. We based our analysis on the responses of neurons to the images of all classes in ImageNet database. In our analysis, we first propose a visualization method to illustrate the learned content of each neuron. Next, we investigate single and multi-faceted neurons based on the diversity of neurons responses to different classes. Finally, we compute the neuronal similarity at each layer and make a comparison between them. Our results demonstrate that the neurons in lower layers exhibit a multi-faceted behavior, whereas the majority of neurons in higher layers comprise single-faceted property and tend to respond to a smaller number of classes.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1811.00161

PDF

http://arxiv.org/pdf/1811.00161


Similar Posts

Comments