Evaluating Scalable Uncertainty Estimation Methods for DNN-Based Molecular Property Prediction

no code implementations • 7 Oct 2019 • Gabriele Scalia, Colin A. Grambow, Barbara Pernici, Yi-Pei Li, William H. Green

Advances in deep neural network (DNN) based molecular property prediction have recently led to the development of models of remarkable accuracy and generalization ability, with graph convolution neural networks (GCNNs) reporting state-of-the-art performance for this task.

Bayesian Inference Molecular Property Prediction +2