Patent · US Active

Apparatus and methods for efficient updates in spiking neuron network

US9256823B2 · kind B2 · utility

9Cited by
19References
24Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 27, 2012
Grant dateFeb 9, 2016
Priority date
Expiry dateJan 9, 2034

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/049
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Efficient updates of connections in artificial neuron networks may be implemented. A framework may be used to describe the connections using a linear synaptic dynamic process, characterized by stable equilibrium. The state of neurons and synapses within the network may be updated, based on inputs and outputs to/from neurons. In some implementations, the updates may be implemented at regular time intervals. In one or more implementations, the updates may be implemented on-demand, based on the network activity (e.g., neuron output and/or input) so as to further reduce computational load associated with the synaptic updates. The connection updates may be decomposed into multiple event-dependent connection change components that may be used to describe connection plasticity change due to neuron input. Using event-dependent connection change components, connection updates may be executed on per neuron basis, as opposed to per-connection basis.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.