SPIKING NEURAL NETWORK OBJECT RECOGNITION APPARATUS AND METHODS

Number of patents in Portfolio can not be more than 2000

United States of America Patent

APP PUB NO 20130297539A1
SERIAL NO

13465918

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

Apparatus and methods for feedback in a spiking neural network. In one approach, spiking neurons receive sensory stimulus and context signal that correspond to the same context. When the stimulus provides sufficient excitation, neurons generate response. Context connections are adjusted according to inverse spike-timing dependent plasticity. When the context signal precedes the post synaptic spike, context synaptic connections are depressed. Conversely, whenever the context signal follows the post synaptic spike, the connections are potentiated. The inverse STDP connection adjustment ensures precise control of feedback-induced firing, eliminates runaway positive feedback loops, enables self-stabilizing network operation. In another aspect of the invention, the connection adjustment methodology facilitates robust context switching when processing visual information. When a context (such an object) becomes intermittently absent, prior context connection potentiation enables firing for a period of time. If the object remains absent, the connection becomes depressed thereby preventing further firing.

Loading the Abstract Image... loading....

First Claim

See full text

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddress
BRAIN CORPORATION10182 TELESIS CT SUITE 100 SAN DIEGO CA 92121

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Izhikevich, Eugene San Diego, US 78 2945
Petre, Csaba San Diego, US 36 2475
Piekniewski, Filip San Diego, US 44 1910
Szatmary, Botond San Diego, US 53 3204

Cited Art Landscape

Load Citation

Patent Citation Ranking

Forward Cite Landscape

Load Citation