Citrine Informatics

Working at Citrine offers the rare opportunity to collaborate with applied scientists at the leading edge of statistical learning theory and application. Here are a few representative peer-reviewed publications describing research done at Citrine in support of the platform’s AI capabilities: Assessing the Frontier: Active Learning, Model Accuracy, and Multi-objective Materials Discovery and Optimization (2019). at https://arxiv.org/abs/1911.03224 Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery (2018). at https://doi.org/10.1039/C8ME00012C Overcoming data scarcity with transfer learning. (2017). at https://arxiv.org/abs/1711.05099 High-Dimensional Materials and Process Optimization Using Data-Driven Experimental Design with Well-Calibrated Uncertainty Estimates. (2017). at https://doi.org/10.1007/s40192-017-0098-z