Event-based reasoning and learning on probabilistic spiking Bayesian networks

摘要

A method of performing event-based Bayesian reasoning and learning involves receiving an input event at each node. The method also includes adding a bias weight and / or a coupling weight to the input event to obtain an intermediate value. The method further includes determining a node state based on the intermediate value. In addition, the method includes computing an output event rate that represents a posteriori probability based on the node state to generate an output event by a probabilistic point process.