Kobi Felton
Papers
1
Total Citations
76
H-Index
1
About
Kobi Felton is a pioneering researcher at the intersection of machine learning, robotics, and formulation science. His work centers on revolutionizing how complex formulated products—from pharmaceuticals to consumer goods—are developed, replacing slow, intuition-driven trial-and-error with accelerated, data-driven experimentation. Felton’s most influential contribution is the integration of machine learning classification algorithms with Thompson sampling, a Bayesian optimization method, to guide robotic experiments in real time. This approach, detailed in his highly cited 2021 paper (76 citations), enables the efficient exploration of vast formulation spaces, dramatically reducing time to market for new products. By coupling automated lab hardware with intelligent decision-making, Felton has established a new paradigm for “self-driving” laboratories in materials science. His work not only demonstrates significant practical impact—slashing development cycles from months to days—but also provides a generalizable framework for optimizing complex mixtures where traditional physical models fall short. Felton’s research is a landmark in the growing field of autonomous experimentation, inspiring a new generation of researchers to rethink how we discover and optimize functional materials.
Research Focus
Key Achievements
Top Papers
- 1