Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Process for forming synapses in neural networks and resistor therefor

Patent ·
OSTI ID:870526
 [1]
  1. San Francisco, CA
+ Show Author Affiliations

Customizable neural network in which one or more resistors form each synapse. All the resistors in the synaptic array are identical, thus simplifying the processing issues. Highly doped, amorphous silicon is used as the resistor material, to create extremely high resistances occupying very small spaces. Connected in series with each resistor in the array is at least one severable conductor whose uppermost layer has a lower reflectivity of laser energy than typical metal conductors at a desired laser wavelength.

Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA
DOE Contract Number:
W-7405-ENG-48
Assignee:
Regents of University of California (Oakland, CA)
Patent Number(s):
US 5538915
OSTI ID:
870526
Country of Publication:
United States
Language:
English

References (3)

Resistive synaptic interconnects for electronic neural networks
  • Lamb, J. L.; Thakoor, A. P.; Moopenn, A.
  • Journal of Vacuum Science & Technology A: Vacuum, Surfaces, and Films, Vol. 5, Issue 4 https://doi.org/10.1116/1.574607
journal July 1987
An introduction to computing with neural nets journal January 1987
A laser direct write double-level-metal technology for rapid fabrication conference January 1990

Similar Records

Process for forming synapses in neural networks and resistor therefor
Patent · Tue Jul 23 00:00:00 EDT 1996 · OSTI ID:264572
Laser programmable integrated curcuit for forming synapses in neural networks
Patent · Tue Dec 31 23:00:00 EST 1996 · OSTI ID:870831
Laser programmable integrated circuit for forming synapses in neural networks
Patent · Mon Feb 10 23:00:00 EST 1997 · OSTI ID:441872

Related Subjects

/438/
amorphous
amorphous silicon
array
conductor
conductors
connected
create
customizable
customizable neural
desired
doped
energy
extremely
form
forming
forming synapses
highly
highly doped
identical
issues
laser
laser energy
laser wavelength
layer
material
metal
metal conduct
metal conductor
metal conductors
network
networks
neural
neural net
neural network
neural networks
occupying
process
processing
processing issues
reflectivity
resistances
resistor
resistor material
resistors
resistors form
series
severable
silicon
simplifying
spaces
synapse
synapses
synaptic
synaptic array
typical
uppermost
uppermost layer
wavelength