New Software Leverages Prediction Uncertainty to Optimize Deep Learning Models

A team of Berkeley Lab researchers has developed HYPPO, an open-source software tool for hyperparameter optimization of deep neural networks used in scientific research. HYPPO leverages prediction uncertainty to optimize deep learning models for science. Click here to learn more. https://cs.lbl.gov/news-media/news/2022/hyppo-leveraging-prediction-uncertainty-to-optimize-deep-learning-models-for-science/