Bgolearn

Overview

Bgolearn is an open-source platform designed to enhance material design through advanced Bayesian optimization techniques. With powerful tools for regression, classification, and multi-objective optimization, Bgolearn empowers researchers and engineers to efficiently explore material properties and design parameters.

Key Components

The core module offering powerful regression, classification, and efficiency testing tools. Optimized for material property prediction and analysis.

MultiBgolearn

Focuses on multi-objective Bayesian optimization. Enables the simultaneous optimization of multiple objectives, with flexible surrogate model selection.

BgoFace

A user-friendly graphical interface for interacting with Bgolearn. It simplifies the process of running optimization tasks and visualizing results.

Installation

To install Bgolearn and its modules, run the following commands:

pip install Bgolearn
pip install MultiBgolearn

Documentation

Contact

For more information or support, feel free to reach out:

Email: bcao686@connect.hkust-gz.edu.cn
GitHub: Bgolearn GitHub Repository

About the Author

Dr. Bin Cao is deeply passionate about AI-driven computational materials research, with a focus on crystallography structure analysis and Bayesian optimization techniques for material design. He is currently researched with HKUST (GZ). For more details, visit his homepage

Obtained Software Patents

Double-click an image to enlarge, double-click again to restore.

Research Articles Using Bgolearn

Bgolearn has been applied in various research studies focused on material design and optimization. Explore the research articles that cite Bgolearn:

View Research Articles on Google Scholar