Explain what you see

In this thesis, we have introduced new techniques for the problems of open-ended learning, online incremental learning, and explainable learning. These methods have applications in the classification of tabular data, 3D object category recognition, and 3D object parts segmentation. We have utilized argumentation theory and probability theory to develop these methods. 

Dissertation: https://hdl.handle.net/11370/800a925a-f7e8-4c9a-880e-2a37cc319ab8