Automated Inference of Excitable Cell Models as Hybrid Automata

In this paper, we explore from an experimental point of view the possibilities and limitations of the new HYCGE learning algorithm for hybrid automata. As an example of a practical application, we study the algorithm’s performance on learning the behaviour of the action potential in excitable cells, specifically the Hodgkin-Huxley model of a squid giant axon, the Luo-Rudy model of a guinea pig ventricular cell, and the Entcheva model of a neonatal rat ventricular cell. The validity and accuracy of the algorithm is also visualized through graphical means.