Anomaly detection with spiking neural networks
Abstract
Detecting anomalies with a spiking neural network is provided. An input layer receives a number of inputs and converts them into phase-coded spikes, wherein each input is contained within a number of progressively larger neighborhoods of surrounding inputs. From the phase-coded spikes, a median value of each input is computed for each size neighborhood. An absolute difference of each input from its median value is computed for each size neighborhood. A median absolute difference (MAD) of each input is computed for each size neighborhood. For each input, an adaptive median filter (AMF) determines if a MAD for any size neighborhood exceeds a respective threshold. If one or more neighborhoods exceeds its threshold, the AMF outputs the median value of the input for the smallest neighborhood. If none of the neighborhoods exceeds the threshold, the AMF outputs the original value of the input.
- Inventors:
- Issue Date:
- Research Org.:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1925071
- Patent Number(s):
- 11436475
- Application Number:
- 16/436,744
- Assignee:
- National Technology & Engineering Solutions of Sandia, LLC (Albuquerque, NM)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- DOE Contract Number:
- NA0003525
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 06/10/2019
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Verzi, Stephen Joseph, Vineyard, Craig Michael, and Aimone, James Bradley. Anomaly detection with spiking neural networks. United States: N. p., 2022.
Web.
Verzi, Stephen Joseph, Vineyard, Craig Michael, & Aimone, James Bradley. Anomaly detection with spiking neural networks. United States.
Verzi, Stephen Joseph, Vineyard, Craig Michael, and Aimone, James Bradley. Tue .
"Anomaly detection with spiking neural networks". United States. https://www.osti.gov/servlets/purl/1925071.
@article{osti_1925071,
title = {Anomaly detection with spiking neural networks},
author = {Verzi, Stephen Joseph and Vineyard, Craig Michael and Aimone, James Bradley},
abstractNote = {Detecting anomalies with a spiking neural network is provided. An input layer receives a number of inputs and converts them into phase-coded spikes, wherein each input is contained within a number of progressively larger neighborhoods of surrounding inputs. From the phase-coded spikes, a median value of each input is computed for each size neighborhood. An absolute difference of each input from its median value is computed for each size neighborhood. A median absolute difference (MAD) of each input is computed for each size neighborhood. For each input, an adaptive median filter (AMF) determines if a MAD for any size neighborhood exceeds a respective threshold. If one or more neighborhoods exceeds its threshold, the AMF outputs the median value of the input for the smallest neighborhood. If none of the neighborhoods exceeds the threshold, the AMF outputs the original value of the input.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2022},
month = {9}
}
Works referenced in this record:
A Hybrid Network Anomaly and Intrusion Detection Approach Based on Evolving Spiking Neural Network Classification
book, January 2014
- Demertzis, Konstantinos; Iliadis, Lazaros
- Communications in Computer and Information Science
Neural-Inspired Anomaly Detection
book, January 2018
- Verzi, Stephen J.; Vineyard, Craig M.; Aimone, James B.
- Unifying Themes in Complex Systems IX
Adaptive impulse detection using center-weighted median filters
journal, January 2001
- Chen, T.
- IEEE Signal Processing Letters, Vol. 8, Issue 1