The content explores adjusting the dynamics of the Hopfield Neural Network (HNN) through time-variant stimuli, highlighting the impact of Weight Matrix Stimulus (WMS) and State Variable Stimulus (SVS) on attractor formation. The study delves into the diverse attractor outcomes based on different stimulus combinations, emphasizing the importance of suitable adjustments for enhancing network dynamics. The implementation of the dynamically adjusted HNN on an FPGA platform and its application in image encryption for secure communication are detailed. The paper is structured into sections focusing on the model of the adjusted HNN, the dynamics analysis, FPGA implementation, and image encryption scheme.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Xuenan Peng,... at arxiv.org 03-01-2024
https://arxiv.org/pdf/2402.18584.pdfDeeper Inquiries