Libmoon is a flexible and extensible multi-objective optimization platform. Our goal is to make MOO great again. We released libmoon not because developing MOO is easy, but because it is hard.

pipeDejavu: Hardware-aware Latency Predictable, Differentiable Search for Faster Config and Convergence of Distributed ML Pipeline Parallelism

Selected Paper from the AI-CyberSec 2021 Workshop in the 41st SGAI International Conference on Artificial Intelligence (MDPI Journal Electronics)

We're proud to announce that our team secured the First Prize in the BCG GAMMA Challenge for Data Science and Consulting. This GitHub repository hosts all the code, models, and analytical techniques we employed during the competition.

Gait Recognition with 3D CNN. This project proposes a novel approach using 3D convolutional neural networks (3D CNN) to capture spatio-temporal features of gait sequences for robust recognition in an un-intrusive manner.

A Python package for machine learning pipeline optimization

GUI for hyperparameter optimizer and plotting experiment results