A machine-learning based method that can accurately predict relevant aspects of the behavior of synapses, such as the activation of synaptic receptors, at very low computational cost. The method is designed to learn patterns and general principles from previous Monte Carlo simulations and to predict synapse behavior from them. The resulting procedure is accurate, automatic and can predict synapse behavior under experimental conditions that are different to the ones used during the learning phase. Since our method efficiently reduces the computational costs, it is suitable for the simulation of the vast number of synapses that occur in the mammalian brain.
Model Type: Synapse
Model Concept(s): Simplified Models
Implementer(s): Montes, Jesus [jmontes at cesvima.upm.es]
Montes J, Gomez E, Merchán-Pérez A, Defelipe J, Peña JM. (2013). A machine learning method for the prediction of receptor activation in the simulation of synapses. PloS one. 8 [PubMed]