Devices and methods for increasing the speed or power efficiency of a computer when performing machine learning using spiking neural networks
Abstract
A method for increasing a speed and efficiency of a computer when performing machine learning using spiking neural networks. The method includes computer-implemented operations; that is, operations that are solely executed on a computer. The method includes receiving, in a spiking neural network, a plurality of input values upon which a machine learning algorithm is based. The method also includes correlating, for each input value, a corresponding response speed of a corresponding neuron to a corresponding equivalence relationship between the input value to a corresponding latency of the corresponding neuron. Neurons that trigger faster than other neurons represent close relationships between input values and neuron latencies. Latencies of the neurons represent data points used in performing the machine learning. A plurality of equivalence relationships are formed as a result of correlating. The method includes performing the machine learning using the plurality of equivalence relationships.
- Inventors:
- Issue Date:
- Research Org.:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 2222329
- Patent Number(s):
- 11755891
- Application Number:
- 16/013,810
- Assignee:
- National Technology & Engineering Solutions of Sandia, LLC (Albuquerque, NM)
- DOE Contract Number:
- NA0003525
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 06/20/2018
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Vineyard, Craig Michael, Severa, William Mark, Aimone, James Bradley, and Verzi, Stephen Joseph. Devices and methods for increasing the speed or power efficiency of a computer when performing machine learning using spiking neural networks. United States: N. p., 2023.
Web.
Vineyard, Craig Michael, Severa, William Mark, Aimone, James Bradley, & Verzi, Stephen Joseph. Devices and methods for increasing the speed or power efficiency of a computer when performing machine learning using spiking neural networks. United States.
Vineyard, Craig Michael, Severa, William Mark, Aimone, James Bradley, and Verzi, Stephen Joseph. Tue .
"Devices and methods for increasing the speed or power efficiency of a computer when performing machine learning using spiking neural networks". United States. https://www.osti.gov/servlets/purl/2222329.
@article{osti_2222329,
title = {Devices and methods for increasing the speed or power efficiency of a computer when performing machine learning using spiking neural networks},
author = {Vineyard, Craig Michael and Severa, William Mark and Aimone, James Bradley and Verzi, Stephen Joseph},
abstractNote = {A method for increasing a speed and efficiency of a computer when performing machine learning using spiking neural networks. The method includes computer-implemented operations; that is, operations that are solely executed on a computer. The method includes receiving, in a spiking neural network, a plurality of input values upon which a machine learning algorithm is based. The method also includes correlating, for each input value, a corresponding response speed of a corresponding neuron to a corresponding equivalence relationship between the input value to a corresponding latency of the corresponding neuron. Neurons that trigger faster than other neurons represent close relationships between input values and neuron latencies. Latencies of the neurons represent data points used in performing the machine learning. A plurality of equivalence relationships are formed as a result of correlating. The method includes performing the machine learning using the plurality of equivalence relationships.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Sep 12 00:00:00 EDT 2023},
month = {Tue Sep 12 00:00:00 EDT 2023}
}