Litcius/Paper detail

Active learning of chemical reaction networks<i>via</i>probabilistic graphical models and Boolean reaction circuits

Maximilian Cohen, Tejas Goculdas, Dionisios G. Vlachos

2022Reaction Chemistry & Engineering12 citationsDOIOpen Access PDF

Abstract

Reaction networks are identified with active learning design of experiments using Bayesian statistics and Boolean principles in a generalizable methodology.

Topics & Concepts

Bayesian networkComputer scienceProbabilistic logicGraphical modelBoolean functionElectronic circuitTheoretical computer scienceMachine learningArtificial intelligenceAlgorithmEngineeringElectrical engineeringAnalytical Chemistry and ChromatographyAdvanced Control Systems OptimizationGene Regulatory Network Analysis
Active learning of chemical reaction networks<i>via</i>probabilistic graphical models and Boolean reaction circuits | Litcius