no code implementations • 2 Jun 2023 • Jamshid Sourati, James Evans
Artificial intelligence (AI) models trained on published scientific findings have been used to invent valuable materials and targeted therapies, but they typically ignore the human scientists who continually alter the landscape of discovery.
no code implementations • 2 Jul 2022 • Jamshid Sourati, James Evans
When we evaluate the promise of our predictions with first-principles equations, we demonstrate that increased complementarity of our predictions does not decrease and in some cases increases the probability that the predictions possess the targeted properties.
no code implementations • 12 Apr 2021 • Jamshid Sourati, James Evans
These AI approaches typically ignore the distribution of human prediction engines -- scientists and inventor -- who continuously alter the landscape of discovery and invention.
2 code implementations • CVPR 2022 • Prateek Munjal, Nasir Hayat, Munawar Hayat, Jamshid Sourati, Shadab Khan
Finally, we conclude with a set of recommendations on how to assess the results using a new AL algorithm to ensure results are reproducible and robust under changes in experimental conditions.
Ranked #6 on Active Learning on CIFAR10 (10,000)
no code implementations • 27 May 2016 • Jamshid Sourati, Murat Akcakaya, Todd K. Leen, Deniz Erdogmus, Jennifer G. Dy
In particular, we show that FIR can be asymptotically viewed as an upper bound of the expected variance of the log-likelihood ratio.