We map inverse transform learning onto spiking networks. We show that the model manages to learn from repeated observations of a variable and samples from the target distribution during spontaneous dynamics.
Simulation Environment: MATLAB
Implementer(s): Maes, Amadeus [amadeus.maes at gmail.com]
Maes A, Barahona M, Clopath C. (accepted). Long- and short-term history effects in a spiking network model of statistical learning Scientific Reports.