AI Article Synopsis
- The paper suggests using superconducting quantum interferometers to create neural networks that consume very little power.
- These networks utilize special components called Josephson cells, which have activation functions shaped like sigmoid and Gaussian curves.
- The authors focus on optimizing these components for popular types of neural networks, specifically three-layer perceptrons and radial basis function networks.
Article Abstract
We propose the concept of using superconducting quantum interferometers for the implementation of neural network algorithms with extremely low power dissipation. These adiabatic elements are Josephson cells with sigmoid- and Gaussian-like activation functions. We optimize their parameters for application in three-layer perceptron and radial basis function networks.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5082478 | PMC |
| http://dx.doi.org/10.3762/bjnano.7.130 | DOI Listing |
Publication Analysis
Top Keywords
adiabatic superconducting
4
superconducting cells
4
cells ultra-low-power
4
ultra-low-power artificial
4
artificial neural
4
neural networks
4
networks propose
4
propose concept
4
concept superconducting
4
superconducting quantum
4
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!