State Estimation for Markovian Jump Neural Networks Under Probabilistic Bit Flips: Allocating Constrained Bit Rates
Yuru Guo, Zidong Wang, Junyi Li, Yong Xu
Abstract
In this article, the state estimation problem is studied for Markovian jump neural networks (MJNNs) within a digital network framework. The wireless communication channel with limited bandwidth is characterized by a constrained bit rate, and the occurrence of bit flips during wireless transmission is mathematically modeled. A transmission mechanism, which includes coding-decoding under bit-rate constraints and considers probabilistic bit flips, is introduced, providing a thorough characterization of the digital transmission process. A mode-dependent remote estimator is designed, which is capable of effectively capturing the internal state of the neural network. Furthermore, a sufficient condition is proposed to ensure the estimation error to remain bounded under challenging network conditions. Within this theoretical framework, the relationship between the neural network's estimation performance and the bit rate is explored. Finally, a simulation example is provided to validate the theoretical findings.