Chaotification for a class of cellular neural networks with distributed delays

In this Letter, the chaotification for a class of cellular neural networks with distributed delays is studied. On the basis of the largest Lyapunov exponent, the sensitivity to the initial conditions is studied for the distributed delays with kernel being weak and strong. Some theoretical results about the chaotification for the neural network with distributed time delays are derived. Finally, two numerical simulations are presented to illustrate the effectiveness of the theoretical results.     

Partially connected feedforward neural networks on Apollonian networks

This paper presents a novel and data-independent method to construct a type of partially connected feedforward neural network (FNN). The proposed networks, called Apollonian network-based partially connected FNNs (APFNNs), are constructed in terms of the structures of two-dimensional deterministic Apollonian networks. The APFNNs are then applied in various experiments to solve function approximation, forecasting and classification problems. Their results are compared with those generated by partially connected FNNs with random connectivity (RPFNNs), different learning algorithm-based traditional FNNs and other benchmark methods. The results demonstrate that the proposed APFNNs have a good capacity to fit complicated input and output relations, and provide better generalization performance than traditional FNNs and RPFNNs. The APFNNs also demonstrate faster training speed in each epoch than traditional FNNs.     

基于逆卷积神经网络的等离子体辐射分布断层重建方法

发展了一种基于逆卷积神经网络的图像级重建方法用于聚变等离子体辐射分布的断层反演.通过引入结构相似度(SSIM)作为损失函数,该方法在模拟数据实验中表现出了较好的重建效果.模拟实验结果表明,在弦积分信号噪声强度为10％、15％及20％时,该方法的重建结果依然具有良好的精确度和鲁棒性.     

Effect of damage in neural networks

The effect of damage on the pattern recognition in the Hopfield-model of neural networks is studied. It is assumed that in a damaged network the synaptic efficaciesJ _i,j=J_j,i, between pairs of neuronsS _i andS _j follow the Hebb rule with probability (1–p) and are equal to zero with probabilityp. Numerical simulations are performed for a net consisting of 400 neurons. It is investigated in detail how the retrieval of noisy patterns and the storage capacity of the net depends, for varying initial noise, on the concentrationp of the damaged synaptic efficacies.     

时滞离散神经网络的同步控制

利用既有效又便于实施的时滞状态反馈控制器,根据所给定的条件构造相应的不等式,研究了带有时滞的离散神经网络模型的同步控制问题,给出了该离散系统指数同步的充分条件.在设计同步控制的时候,没有假设激励函数的有界性、可微性和单调性,给出的条件简便易实施.数值结果进一步证明了该控制方法的有效性. 关键词： 离散神经网络 时滞 同步     

Learning and forgetting on asymmetric,diluted neural networks

It is possible to construct diluted asymmetric models of neural networks for which the dynamics can be calculated exactly. We test several learning schemes, in particular, models for which the values of the synapses remain bounded and depend on the history. Our analytical results on the relative efficiencies of the various learning schemes are qualitatively similar to the corresponding ones obtained numerically on fully connected symmetric networks.     

混沌背景中微弱信号检测的神经网络方法

基于复杂非线性系统相空间重构理论，提出了混沌背景中微弱信号检测的神经网络方法，利用神经网络强大的学习和非线性处理能力，建立了混沌背景噪声的一步预测模型，从预测误差中检测淹没在混沌背景噪声中的微弱目标信号(包括周期信号和瞬态信号)，研究了混沌背景中存在白噪声时该方法的检测能力，指出了目标信号为瞬态信号和周期信号时检测原理的异同点，最后以Lorenz系统作为混沌背景噪声进行了仿真实验，实验表明该方法能有效地将混沌背景中极其微弱的信号检测出来. 关键词： 混沌 神经网络 信号检测     

Photorefraction images analysis through neural networks

The importance of an early evaluation of infants’ visual system condition is long time recognized. Non-corrected visual disorders may lead to major vision and developmental non-reversible limitations in the future. Among the objective methods of refraction, photorefractive techniques are specifically designed for screening young children. Over the years a number of photorefraction systems with different grades of complexity and automation were developed. A critical problem that one needs to deal with in any approach to these systems is the interpretation and classification of the photorefraction images. In digital photorefraction conventional image processing operators and Fourier techniques were currently used. In this communication we will report on the use of Neural Networks for automated classification of digital photorefraction images.     

Overview of hybrid optical neural networks

This paper reviews optical architectures for the implementation of hybrid neural networks. Optics is mainly applied to implementing the matrix-vector or tensor-matrix multiplication. In addition, the general background of neural networks as well as a brief discussion on holographic associative memory are also given.     

Culture and evolution on populations of neural networks

Although acquired characteristics are not incorporated into the genotype, some works have pointed to the influence of learning in evolution. We present a dynamic model of neural networks presenting evolutive features, even without modification in genotype, due to the introduction of culture. Our model presents other features that seem to reproduce some aspects of real world populations.     

Pair-correlated patterns in Hopfield model of neural networks

We study the retrieval properties of the Hopfield model of neural networks when the memorized patterns are statistically correlated in pairs. There is a finite correlationk between the memories of each pair, but memories of different pairs are uncorrelated. The analysis is restricted to the case of an arbitrary but finite number of memories in the thermodynamic limit. We find that there are two retrieval regimes: for 0<T<(1–k) the system recognizes the stored patterns and for (1–k)<T<(1+k) the system is able to recognize pairs, but it is not able to distinguish between its two patterns.     

Synchronization criteria for coupled Hopfield neural networks with time-varying delays

This paper proposes new delay-dependent synchronization criteria for coupled Hopfield neural networks with time-varying delays. By construction of a suitable Lyapunov-Krasovskii's functional and use of Finsler's lemma, novel synchronization criteria for the networks are established in terms of linear matrix inequalities (LMIs) which can be easily solved by various effective optimization algorithms. Two numerical examples are given to illustrate the effectiveness of the proposed methods.     

基于混沌神经网络的盲检测改进新算法

针对Hopfield神经网络的多起点问题,提出了一种新的基于混沌神经网络的盲信号检测算法,实现了二进制移相键控信号盲检测.据此进一步提出双sigmoid混沌神经网络模型,构造了新的能量函数,且证明了该模型的稳定性,并对网络参数进行配置.仿真实验表明:混沌神经网络能够避免局部极小点且具备较强的抗噪性能,双sigmoid混沌神经网络则继承了其所有的优点,且其收敛速度更快,仅需更短的接收数据即可到达全局真实平衡点,从而降低了算法的计算复杂度,减少了运行时间.     

New results on stability criteria for neural networks with time-varying delays

In this paper,the problem of stability analysis for neural networks with time-varying delays is considered.By constructing a new augmented Lyapunov-Krasovskii’s functional and some novel analysis techniques,improved delaydependent criteria for checking the stability of the neural networks are established.The proposed criteria are presented in terms of linear matrix inequalities(LMIs) which can be easily solved and checked by various convex optimization algorithms.Two numerical examples are included to show the superiority of our results.     

Particle sizing by multiangle light-scattering data using the high-order neural networks

The problem of retrieval of size and refractive index of a spherical particle by angular dependence of scattered light in scanning flow cytometry is considered. For its solution, the high-order neural networks are used. We restricted the range of angles available for measurement from 10° to 60°. The retrieval errors of characteristics of nonabsorbing particles were investigated at the ranges of the radius and relative refractive index 0.6–10.6 μm, and 1.02–1.38, respectively.     

混沌时滞神经网络系统的反同步

利用状态观测器方法研究了一类带时滞的混沌神经网络系统的反同步问题.与应用于其他混沌系统的反同步方法相比,提出的方法更为简便,并且利用极点配置技术,只要通过调整特征值来实现反同步速率的快慢.最后,给出了数值例子和计算机仿真结果来验证该方案的有效性. 关键词： 混沌神经网络 状态观测器 极点配置技术 反同步     

人工神经网络在建筑声学中的应用

本文对人工神经网络的历史作了简单回顾，并对它在建筑声学领域中的应用状况作了阐述，同时提出了有待进一步探讨的若干问题。     

More relaxed condition for dynamics of discrete time delayed Hopfield neural networks

The dynamics of discrete time delayed Hopfield neural networks is investigated. By using a difference inequality combining with the linear matrix inequality, a sufficient condition ensuring global exponential stability of the unique equilibrium point of the networks is found. The result obtained holds not only for constant delay but also for time-varying delays.     

More relaxed condition for dynamics of discrete time delayed Hopfield neural networks

The dynamics of discrete time delayed Hopfield neural networks is investigated. By using a difference inequality combining with the linear matrix inequality, a sufficient condition ensuring global exponential stability of the unique equilibrium point of the networks is found. The result obtained holds not only for constant delay but also for time-varying delays.     

Improved delay-dependent exponential stability for uncertain stochastic neural networks with time-varying delays

This Letter investigates the problem of delay-dependent exponential stability analysis for uncertain stochastic neural networks with time-varying delay. Based on the Lyapunov stability theory, improved delay-dependent exponential stability criteria for the networks are established in terms of linear matrix inequalities (LMIs).