Impact of Radiation on Pattern Recognition in Memristor-Based Neuromorphic Circuits
Abstract
By the nature of their dense interconnectivity, future electronic spiking neural networks (SNNs) have the potential to be extraordinarily robust and defect-tolerant, in addition to energy-efficient. In this research, the effects on SNNs of high levels of radiation generated by weapons of mass destruction is explored through advanced modeling and simulation. Effects of this radiation on the spike timing-dependent plasticity learning rule, system stability, and pattern learning ability of the spiking neural network are analyzed.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 2021
- Accession Number
- AD1137552
Entities
People
- Kurtis D. Cantley
Organizations
- Boise State University