Machine Learning in Materials
Ekin discusses the challenges of noisy experimental data in material science and highlights the potential of machine learning to accelerate materials discovery. He shares insights from his recent work on predicting zero Kelvin stability and the ambitious goal of identifying materials stable at finite temperatures, particularly those with technological applications like superconductors and battery materials. Additionally, there’s a focus on improving density functional theory (DFT) to enhance predictive capabilities using advanced data and machine learning techniques.In this clip
From this podcast
Catalyst with Shayle Kann
Can AI revolutionize materials discovery?
Related Questions