Physical Sciences and Mathematics Commons^™

A Novel Feature Maps Covariance Minimization Approach For Advancing Convolutional Neural Network Performance, Bikram Basnet

UNLV Theses, Dissertations, Professional Papers, and Capstones

We present a method for boosting the performance of the Convolutional Neural Network (CNN) by reducing the covariance between the feature maps of the convolutional layers.

In a CNN, the units of a hidden layer are segmented into the feature/activation maps. The units within a feature map share the weight matrix (filter), or in simple terms look for the same feature. A feature map is the output of one filter applied to the previous layer. CNN search for features such as straight lines, and as these features are spotted, they get reported to the feature map. During the learning process, …