MIT researchers find a new way to quantify the uncertainty in molecular energies predicted by neural networks.

  • Post author:
  • Post category:Uncategorized
Neural networks (NNs) are increasingly being used to predict new materials, the rate and yield of chemical reactions, and drug-target interactions, among others. For these applications, they are orders of magnitude faster than traditional methods such as quantum mechanical simulations. The price for this agility, however, is reliability. Because machine learning models only interpolate, they […]