输出采样同步和状态估计在流电荷域内记忆神经网络中,具有泄漏和时间变化的延迟
G Soundararajan1, R Suvetha2, Minvydas Ragulskis1
1Department of Mathematical Modelling, Kaunas University of Technology, Kaunas LT-51368, Lithuania.
概括
本研究介绍了对记忆神经网络的输出采样控制器,使得即使有网络延迟,也可以实现同步和状态估计. 该方法提高了控制性能,克服了带宽限制.
科学领域:
- 神经科学是一个神经科学.
- 控制理论 控制理论
- 复杂的系统复杂的系统.
背景情况:
- 记忆神经网络 (MNN) 呈现出复杂的动态,对于先进的计算至关重要.
- 联网的MNN面临信号延迟和带宽限制的挑战,阻碍了同步和状态估计.
- 输出采样控制为管理这些系统中离散数据传输提供了一种策略.
研究的目的:
- 开发和分析输出采样控制器,用于具有恒定和时间变化的延迟的流电域MNN.
- 调查这些延迟的MNN中同步和状态估计的共存.
- 用实验数据和模拟来验证拟议的理论框架.
主要方法:
- 设计一个当代的输出采样控制器,以分辨系统动态.
- 差异性包含映射用于不连续的memristive切换的应用.
- 使用输入延迟方法来处理不均的采样间隔.
- 开发基于线性矩阵不等式 (LMI) 的条件,使用Lyapunov-Krasovskii函数和积分不等式.
主要成果:
- 在延迟的MNN中获得足够的条件来实现同步和向量状态估计.
- 通过预设数据集来证明控制器在同步和估计状态方面的有效性.
- 数字验证突出泄漏延迟和输出采样对系统性能的影响.
结论:
- 拟议的输出采样控制策略有效地解决了延迟MNN中的同步和状态估计挑战.
- 理论发现是强大的,通过实验数据和模拟分析的视觉验证得到证实.
- 该研究为设计复杂的记忆网络的可靠控制系统提供了有价值的框架.
相关概念视频
01:11Sampling Continuous Time Signal
203
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
In the...
203
01:27State Space Representation
162
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
Consider an RLC circuit, a...
162
01:30Current Growth And Decay In RL Circuits
3.7K
The current growth and decay in RL circuits can be understood by considering a series RL circuit consisting of a resistor, an inductor, a constant source of emf, and two switches. When the first switch is closed, the circuit is equivalent to a single-loop circuit consisting of a resistor and an inductor connected to a source of emf. In this case, the source of emf produces a current in the circuit. If there were no self-inductance in the circuit, the current would rise immediately to a steady...
3.7K
01:17Continuous Charge Distributions
6.8K
Imagine a bucket of water. It contains many molecules, of the order of 1026 molecules. Thus, although it contains discrete elements (molecules) at the microscopic level, macroscopically, it can be considered continuous. Small volume elements of water, infinitesimal compared to the bulk of the bucket's volume, still contain many molecules. Under this framework, quantized matter is approximated as continuous for practical purposes.
The electric charge can also be subjected to an analogical...
The electric charge can also be subjected to an analogical...
6.8K
01:15RC Circuit with Source
897
When a DC source is abruptly applied to an RC (Resistor-Capacitor) circuit, the voltage can be represented as a unit step function. The voltage across the capacitor, known as the step response, characterizes how the circuit reacts to this sudden change in input.
Due to the inherent properties of a capacitor, its voltage cannot change instantaneously. This means that immediately after the switch is closed, the capacitor's voltage remains the same as it was just before the switch was closed.
Due to the inherent properties of a capacitor, its voltage cannot change instantaneously. This means that immediately after the switch is closed, the capacitor's voltage remains the same as it was just before the switch was closed.
897
01:15Sampling Theorem
297
In signal processing, the analysis of continuous-time signals, denoted as x(t), often involves sampling techniques to convert these signals into discrete-time signals. This process is essential for digital representation and manipulation. A critical component in sampling is the train of impulses, characterized by the sampling interval and the sampling frequency. The relationship between these parameters and the original signal's properties dictates the success of the sampling process.
297