Now showing items 1-4 of 4
Affective Sentiment and Emotional Analysis of Pull Request Comments on GitHub
(University of Waterloo, 2017-12-15)
Sentiment and emotional analysis on online collaborative software development forums can be very useful to gain important insights into the behaviors and personalities of the developers. Such information can later on be ...
Trust Region Methods for Training Neural Networks
(University of Waterloo, 2017-11-09)
Artificial feed-forward neural networks (ff-ANNs) serve as powerful machine learning models for supervised classification problems. They have been used to solve problems stretching from natural language processing to ...
Statistical Learning Approaches to Some Classification Problems
(University of Waterloo, 2017-08-01)
Classification is essential in statistical learning. This thesis deals with three topics in classification: multi-label classification, nonparametric multi-class classification and a special type of text categorization ...
A Novel Mathematical Framework for the Analysis of Neural Networks
(University of Waterloo, 2017-08-22)
Over the past decade, Deep Neural Networks (DNNs) have become very popular models for processing large amounts of data because of their successful application in a wide variety of fields. These models are layered, often ...