Project: Visual Analytics for Machine Learning
Description
Master project with Linhao Meng.
My research focuses on empowering the machine learning pipeline with visual analytics (VA) for data scientists and engineers. Model development is a demanding process that involves various tasks about raw data, features, and models. We explore how to support data scientists and engineers in these tasks in a visual interactive way. First, in many existing works, VA is proven to be an effective way to help users understand and analyze their data (including raw data, features, and models). Second, since some tasks, such as model training in the machine learning pipeline, are time-consuming processes, visualization is a good method to monitor them and facilitate the analysis and verification of intermediate results. Last, VA can be used directly to achieve machine learning tasks such as data labeling, feature engineering, and model building as an interactive ML platform.
Details
- Supervisor
-
Linhao Meng