Periodically Intermittent Noise Stabilization Strategy Based on Discrete-Time State and Mode Observations for Impulsive Neural Networks with Random Switching

Blood（2024）SCI 1区

Anhui Univ

Cited 0|Views2

Abstract

In this paper, a periodic intermittent noise stabilization (also known as stochastic feedback control) strategy based on discrete-time state and mode observations is designed for a class of unstable impulsive neural networks with random switching (INNs-RS). This control scheme has two advantages, on the one hand, using noise as a control source can maintain the original state of the system on average. On the other hand, periodic intermittent control based on discrete-time state and mode observations can effectively reduce the cost of control. We first construct a new Lyapunov function and use the stationary distribution of Markov chains to establish the pth moment and almost sure exponential stability of controlled INNs-RS (CINNs-RS) with periodic intermittent noise controllers based on continuous-time observations. Then, by using the comparison principle, the almost sure exponential stability of CINNs-RS with periodic intermittent noise controllers based on discrete-time observations is established, and a method for calculating the upper bound of the interval between observations is provided. Finally, the rationality and feasibility of the control strategy are verified by and simulations.

Translated text

Key words

Periodic intermittent noise stabilization strategy,Impulsive neural networks with random switching,Markov chain,Discrete-time state and mode observations,Stationary distribution

求助PDF

上传PDF

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Upload PDF to Generate Summary

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Data Disclaimer

The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn

Chat Paper

【要点】：本文提出了一种基于离散时间状态和模式观测的周期性间歇噪声稳定策略，用于具有随机切换的不稳定脉冲神经网络，实现了控制效果的优化和控制成本的降低。

【方法】：通过构建新的Lyapunov函数，并利用Markov链的平稳分布，建立了基于连续时间观测和离散时间观测的脉冲神经网络在周期性间歇噪声控制器下的p阶矩和几乎必然指数稳定性。

【实验】：作者通过仿真验证了控制策略的合理性和可行性，具体使用的实验数据集未在摘要中提及，但实验基于连续和离散时间观测的稳定性分析，提供了观测间隔上限的计算方法。