Browsing Theses by Subject "Trust Region Method"
Now showing items 1-2 of 2
-
Effective and Efficient Optimization Methods for Kernel Based Classification Problems
(University of Waterloo, 2014-04-22)Kernel methods are a popular choice in solving a number of problems in statistical machine learning. In this thesis, we propose new methods for two important kernel based classification problems: 1) learning from highly ... -
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 ...