Cortical simulator for object-oriented simulation of a neural network

摘要

Embodiments of the invention relate to a function-level simulator for modeling a neurosynaptic chip. One embodiment comprises simulating a neural network using an object-oriented framework including a plurality of object-oriented classes. Each class corresponds to a component of a neural network. Running a simulation model of the neural network includes instantiating multiple simulation objects from the classes. Each simulation object is an instance of one of the classes.

主权项

1. A method for simulating a neural network using an object-oriented framework, comprising:
defining a plurality of object-oriented classes, wherein each class corresponds to a component of a neural network; and running a simulation model of the neural network by instantiating multiple simulation objects from said classes, wherein each simulation object is an instance of one of said classes; wherein said multiple simulation objects comprise:
at least one neuron simulation object corresponding to a neuron of the neural network;at least one axon simulation object corresponding to an axon of the neural network; andat least one crossbar simulation object corresponding to one or more weighted synaptic connections interconnecting the neuron to the axon.