Award Date
May 2019
Degree Type
Thesis
Degree Name
Master of Science in Computer Science
Department
Computer Science
First Committee Member
Justin Zhan
Second Committee Member
Laxmi Gewali
Third Committee Member
Wolfgang Bein
Fourth Committee Member
Ge Kan
Number of Pages
80
Abstract
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, the convolutional neural network defines what it perceives as important. Each feature map is looking for something else: one feature map could be looking for horizontal lines while the other for vertical lines or curves. Reducing the covariance between the feature maps of a convolutional layer maximizes the variance between the feature maps out of that layer. This supplements the decrement in the redundancy of the feature maps and consequently maximizes the information represented by the feature maps.
Keywords
Artificial Neural Network; Convolutional Neural Network; Covariance; Data Shadow Tween; Feature maps; Image Classification
Disciplines
Computer Sciences
File Format
Degree Grantor
University of Nevada, Las Vegas
Language
English
Repository Citation
Basnet, Bikram, "A Novel Feature Maps Covariance Minimization Approach for Advancing Convolutional Neural Network Performance" (2019). UNLV Theses, Dissertations, Professional Papers, and Capstones. 3569.
http://dx.doi.org/10.34917/15778394
Rights
IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/