Rare-class Learning

Dec 21, 2020

This interdisciplinary study is conducted to find answers to two important questions which researchers often face in both Machine Learning (ML) and Material Science (MS) fields. In this work, we measure the performance of the most popular ML algorithms (more than a dozen) on rare-class learning problem and determine the best learning algorithm for atom type prediction over the Mg-doped ZnO nanoparticles data obtained from the density-functional tight-binding method.

Extreme Gradient Boosting Material Science Cost-sensitive learning Prototype models Machine Learning Kernel methods Support vector machines
Dr. Hasan Kurban
Dr. Hasan Kurban
Computer & Data Scientist

As a Computer Scientist and Machine Learning Researcher, I am passionate about developing intelligent systems that leverage data-driven approaches to address real-world challenges.