Hardware architecture for simulating a neural network of neurons

摘要

Embodiments of the invention relate to a neural network system for simulating neurons of a neural model. One embodiment comprises a memory device that maintains neuronal states for multiple neurons, a lookup table that maintains state transition information for multiple neuronal states, and a controller unit that manages the memory device. The controller unit updates a neuronal state for each neuron based on incoming spike events targeting said neuron and state transition information corresponding to said neuronal state.

主权项

1. A neural network system, comprising:
a memory device that maintains neuronal states for multiple neurons; a lookup table that maintains state transition information for multiple neuronal states, wherein said state transition information for said multiple neuronal states includes a sequence of neuronal states, and wherein said sequence identifies, for at least one neuronal state of said multiple neuronal states, a subsequent neuronal state that said at least one neuronal state transitions to; and a controller unit that manages said memory device, wherein said controller unit updates a neuronal state for each neuron based on incoming spike events targeting said neuron and state transition information corresponding to said neuronal state.