A New Chaotic Parameters Disturbance Annealing Neural Network for Solving Global Optimization Problems

Since there were few chaotic neural networks applicable to the global optimization, in this paper, we proposea new neural network model - chaotic parameters disturbance annealing (CPDA) network, which is superior to otherexisting neural networks, genetic algorithms, and simulated annealing algorithms in global optimization. In the presentCPDA network, we add some chaotic parameters in the energy function, which make the Hopfield neural network escapefrom the attraction of a local minimal solution and with the parameter p1 annealing, our model will converge to theglobal optimal solutions quickly and steadily. The converge ability and other characters are also analyzed in this paper.The benchmark examples show the present CPDA neuralnetwork's merits in nonlinear global optimization.     

Chaotic Dynamics in Weight Space of Neural Networks

When a special nonlinear self-feedback term is introduced into the dynamical equation of the backpropagation training algorithm for networks, the dynamics in weight space of networks can become chaotic. Chaotic dynamics of the system can help it escape from the most commonplace local minima of the energy. Simulation on the XOR problem and the prediction of chaotic time series have shown that the proposed chaotic training algorithm can converge to the global minimum or its approximate solutions efficiently and dramatically faster than the original backpropagation training algorithm.     

Nonlinear Time Series Prediction Using Chaotic Neural Networks

A nonlinear feedback term is introduced into the evaluation equation of weights of the backpropagation algorithm for neural network,the network becomes a chaotic one.For the purpose of that we can investigate how the different feedback terms affect the process of learning and forecasting,we use the model to forecast the nonlinear time series which is produced by Makey-Glass equation.By selecting the suitable feedback term,the system can escape from the local minima and converge to the global minimum or its approximate solutions,and the forecasting results are better than those of backpropagation algorithm.     

A Novel Image Encryption Algorithm Based on Improved Arnold Transform and Chaotic Pulse-Coupled Neural Network

Information security has become a focal topic in the information and digital age. How to realize secure transmission and the secure storage of image data is a major research focus of information security. Aiming at this hot topic, in order to improve the security of image data transmission, this paper proposes an image encryption algorithm based on improved Arnold transform and a chaotic pulse-coupled neural network. Firstly, the oscillatory reset voltage is introduced into the uncoupled impulse neural network, which makes the uncoupled impulse neural network exhibit chaotic characteristics. The chaotic sequence is generated by multiple iterations of the chaotic pulse-coupled neural network, and then the image is pre-encrypted by XOR operation with the generated chaotic sequence. Secondly, using the improved Arnold transform, the pre-encrypted image is scrambled to further improve the scrambling degree and encryption effect of the pre-encrypted image so as to obtain the final ciphertext image. Finally, the security analysis and experimental simulation of the encrypted image are carried out. The results of quantitative evaluation show that the proposed algorithm has a better encryption effect than the partial encryption algorithm. The algorithm is highly sensitive to keys and plaintexts, has a large key space, and can effectively resist differential attacks and attacks such as noise and clipping.     

Neural Network Structure Optimization by Simulated Annealing

A critical problem in large neural networks is over parameterization with a large number of weight parameters, which limits their use on edge devices due to prohibitive computational power and memory/storage requirements. To make neural networks more practical on edge devices and real-time industrial applications, they need to be compressed in advance. Since edge devices cannot train or access trained networks when internet resources are scarce, the preloading of smaller networks is essential. Various works in the literature have shown that the redundant branches can be pruned strategically in a fully connected network without sacrificing the performance significantly. However, majority of these methodologies need high computational resources to integrate weight training via the back-propagation algorithm during the process of network compression. In this work, we draw attention to the optimization of the network structure for preserving performance despite compression by pruning aggressively. The structure optimization is performed using the simulated annealing algorithm only, without utilizing back-propagation for branch weight training. Being a heuristic-based, non-convex optimization method, simulated annealing provides a globally near-optimal solution to this NP-hard problem for a given percentage of branch pruning. Our simulation results have shown that simulated annealing can significantly reduce the complexity of a fully connected network while maintaining the performance without the help of back-propagation.     

A Novel Color Image Encryption Scheme Based on Hyperchaos and Hopfield Chaotic Neural Network

Problems such as insufficient key space, lack of a one-time pad, and a simple encryption structure may emerge in existing encryption schemes. To solve these problems, and keep sensitive information safe, this paper proposes a plaintext-related color image encryption scheme. Firstly, a new five-dimensional hyperchaotic system is constructed in this paper, and its performance is analyzed. Secondly, this paper applies the Hopfield chaotic neural network together with the novel hyperchaotic system to propose a new encryption algorithm. The plaintext-related keys are generated by image chunking. The pseudo-random sequences iterated by the aforementioned systems are used as key streams. Therefore, the proposed pixel-level scrambling can be completed. Then the chaotic sequences are utilized to dynamically select the rules of DNA operations to complete the diffusion encryption. This paper also presents a series of security analyses of the proposed encryption scheme and compares it with other schemes to evaluate its performance. The results show that the key streams generated by the constructed hyperchaotic system and the Hopfield chaotic neural network improve the key space. The proposed encryption scheme provides a satisfying visual hiding result. Furthermore, it is resistant to a series of attacks and the problem of structural degradation caused by the simplicity of the encryption system’s structure.     

人工神经网络及其在光谱分析中的应用

介绍了人工神经网络的原理及研究进展,对典型神经网络系统作了详细的介绍,对人工神经网络在光谱分析中的应用做了较全面的评述。人工神经网络已成为光谱分析中重要的研究方法之一。     

Discontinuity and Complex Dynamics of Neural Networks

We focus on the discontinuity of a neural network model with diluted and clipped synaptic connections (±l only). The exact evolution rule of the average firing rate becomes a discontinuous piece-wise nonlinear map when very simple functions of dynamical threshold are introduced into the network. Complex dynamics is observed.     

A Color Image Encryption Algorithm Based on Double Fractional Order Chaotic Neural Network and Convolution Operation

A color image encryption algorithm based on double fractional order chaotic neural network (CNN), interlaced dynamic deoxyribonucleic acid (DNA) encoding and decoding, zigzag confusion, bidirectional bit-level diffusion and convolution operation is proposed. Firstly, two fractional order chaotic neural networks (CNNs) are proposed to explore the application of fractional order CNN in image encryption. Meanwhile, spectral entropy (SE) algorithm shows that the sequence generated by the proposed fractional order CNNs has better randomness. Secondly, a DNA encoding and decoding encryption scheme with evolutionary characteristics is adopted. In addition, convolution operation is utilized to improve the key sensitivity. Finally, simulation results and security analysis illustrate that the proposed algorithm has high security performance and can withstand classical cryptanalysis attacks.     

混沌神经动力学行为在多自由度机器人上的应用研究

本文把混沌神经动力学行为应用到了一个多自由度的机器人手臂,利用一种简单的神经编码方法使高维的神经网络模式转化成了低维的运动参数。虽然只在神经网络中嵌入了三种简单的姿势动作,但是在混沌神经动力学行为出现时,机器人手臂呈现出复杂的组合运动。利用这一点,提出了一个简单的控制算法用来解决病态问题(不一定有解或者确定的解无法保证的问题)。实装实验进一步表明,尽管只有粗略甚至不确定的光源信息,利用提出的算法机器人手臂可以成功的寻找到光源。     

Current Oscillation and dc-Voltage-Controlled Chaotic Dynamics in Semiconductor Superlattices

We report a detailed theoretical study of current oscillation and dc-voltage-controlled chaotic dynamics in doped GaAs/AlAs resonant tunneling superlattices under crossed electric and magnetic fields. When the superlattice is biased at the negative differential velocity region, current self-oscillation is observed with proper doping concentration. The current oscillation mode and oscillation frequency can be affected by the dc voltage bias, doping density, and magnetic field. When an ac electric field with fixed amplitude and frequency is also applied to the system, different nonlinear properties show up in the external circuit with the change of dc voltage bias. We carefully study these nonlinear properties with different chaos-detecting methods.     

混沌光学系统之前向神经网络混沌加速的系统辨识研究

研究了利用前向神经网络对混沌光学系统进行混沌加速系统辨识的可能性，计算机数值仿真发现，利用三层前向神经网络混沌光学系统辨识器。在基于混沌动力学角度的修正ＢＰ算法（混沌加速ＢＰ算法）支持下可克服由常规ＢＰ算法导致的辨识时间长的缺点，在较少的训练次数内即可对布拉格声双稳混沌系统进行良好的系统辨识，此研究结果表明，在混沌加速ＢＰ算法支持下，三层前向神经网络可用来快速处理混沌光学时间序列以进行相应的动力学     

人工神经网络在超声无损检测中的应用

人工神经网络对于超声无损检测的发展具有重要的意义，本文对国内外人工神经网络在超声无损检测中应用研究做了较为详细的介绍和分析，指出人工神经网络是实现超声无损检测测定量化的有效途径。     

Time Series Prediction Based on Chaotic Attractor

A new prediction technique is proposed for chaotic time series. The usefulness of the technique is thatit can kick off some false neighbor points which are not suitable for the local estimation of the dynamics systems. Atime-delayed embedding is used to reconstruct the underlying attractor, and the prediction model is based on the timeevolution of the topological neighboring in the phase space. We use a feedforward neural network to approximate thelocal dominant Lyapunov exponent, and choose the spatial neighbors by the Lyapunov exponent. The model is testedfor the Mackey-Glass equation and the convection amplitude of lorenz systems. The results indicate that this predictiontechnique can improve the prediction of chaotic time series.     

基于粒子群优化算法的测光红移回归预测

星系的红移在天文研究中极其重要,星系测光红移的预测对研究宇宙大尺度结构及演变有着重要的研究意义。利用斯隆巡天项目发布的SDSS DR13的150 000个星系的测光及光谱数据进行分析,首先根据颜色特征并基于聚类的方法对星系进行分类,由分类结果可知早型星系的占比较大。对比了三种不同的机器学习算法对早型星系进行测光红移回归预测实验,并找出最优的方法。实验中将星系样本中u, g, r, i, z五个波段的测光值以及两两做差得到的10个颜色特征作为输入数据,首先构建BP网络,使用BP算法对星系的测光红移进行回归预测;然后利用遗传算法（GA）优化BP网络各层参数,将优化后的GA-BP算法应用于早型星系的回归预测试验中。考虑到GA算法的复杂操作会影响预测效率,并且粒子群算法（PSO）不仅稳定性高且操作简单,因此将粒子群算法应用到星系样本中早型星系的测光红移回归预测实验中,进而采用粒子群算法优化BP网络（PSO-BP）。实验中将光谱红移作为期望值,采用均方差（MSE）作为误差分析指标来评判三种算法的精度,将PSO-BP回归预测结果与BP网络模型、GA-BP网络模型进行比较。由实验结果可知,BP网络的MSE值为0.001 92,GA-BP网络的MSE值0.001 728,PSO-BP网络的MSE值为0.001 708。实验结果表明,所用到的PSO-BP优化模型在精度上优于BP神经网络模型和GA-BP神经网络模型,分别提高了11.1%和1.2%;在效率上优于传统的K近邻（KNN）测光红移估计算法, 克服了KNN算法中遍历所有数据样本进行训练的缺点并且其泛化性能优于其它BP网络优化模型。     

Time Series Prediction Based on Chaotic Attractor

A new prediction technique is proposed for chaotic time series. The usefulness of the technique is that it can kick off some false neighbor points which are not suitable for the local estimation of the dynamics systems. A time-delayed embedding is used to reconstruct the underlying attractor, and the prediction model is based on the time evolution of the topological neighboring in the phase space. We use a feedforward neural network to approximate the local dominant Lyapunov exponent, and choose the spatial neighbors by the Lyapunov exponent. The model is tested for the Mackey-Glass equation and the convection amplitude of lorenz systems. The results indicate that this prediction technique can improve the prediction of chaotic time series.     

人工神经网络用于荧光分析法同时测定苯酚和间苯二酚的含量

本文应用人工神经网络原理，以Levenberg-Marquardt BP算法对荧光光谱严重重叠的苯酚、间苯二酚的混合体系进行同时测定，在290－345nm的范围内，以14个特征波长处的荧光强度值作为网络特征参数，并通过均匀设计安排样本进行网络训练和计算，网络训练8次即达到误差精度要求（误差平方和小于0.01）。苯酚、间苯二酚的平均回收率分别为100.2%，９９.99%，相对标准偏差分别为０.４％，１.3％。     

人工神经元网络在光谱识别中的应用

本文利用人工神经网络原理设计了一神经元网络,进行了光谱识别实验,当训练光谱与待识别光谱具有相同的定标情形下,网络具有较高的识别率,可以实用。     

人工神经网络用于光度法同时测定铜钴镍

本文采用PAR－Cu,Co,Ni显色体系,应用人工神经网络原理,以Levenberg-MarguardtBP算法,对紫外吸收光谱严重重叠的三组分金属配合物体系进行含量测定。在452－552nm的范围内,以14个特征波长处的吸收值作为网络特征参数,并通过正交设计安排样本。网络仅训练781次即可达到要求,Cu,Co,Ni三者的平均回收率分别为99．99％,99．97％,测定结果的相对标准偏差分别为0．1％,0．2％,0．1％。实验表明,该方法与现有的算法相比具有训练速度快,预测结果准确度高等特点。该方法和光度法结合有望成为多组分分析的有效方法之一。     

Effects of Coupling Distance on Synchronization and Coherence in Chaotic Neural Networks

Effects of coupling distance on synchronization and coherence of chaotic neurons in complex networks are numerically investigated. We find that it is not beneficial to neurons synchronization if confining the coupling distance of random edges to a limit dmax, but help to improve their coherence. Moreover, there is an optimal value of dmax at which the coherence is maximum.