Rapid Exploration of a 32.5M Compound Chemical Space with Active Learning to Discover Density Functional Approximation Insensitive and Synthetically Accessible Transitional Metal Chromophores.
Chenru DuanAditya NandyGianmarco TerronesDavid W. KastnerHeather J. KulikPublished in: CoRR (2022)
Keyphrases
- active learning
- semi supervised
- learning strategies
- active exploration
- vector space
- random sampling
- search space
- space time
- closed form
- machine learning
- exploration exploitation
- selective sampling
- parameter space
- pool based active learning
- active learning strategies
- maximum error
- design space
- queueing networks
- cost sensitive
- low dimensional
- pairwise