Modeling birdsong learning with a chaotic Elman network

Among passerines, Bengali finches are known to sing extremely complex courtship songs with three hierarchical structures: namely, the element, the chunk, and the syntax. In this work, we theoretically studied the mechanism of the song of Bengali finches in aides to provide a dynamic view of the development of birdsong learning. We first constructed a model of the Elman network with chaotic neurons that successfully learned the supervisor signal defined by a simple finite-state syntax. Second, we focused on the process of individual-specific increases in the complexity of song syntax. We propose a new learning algorithm to produce the intrinsic diversification of song syntax without a supervisor on the basis of the itinerant dynamics of chaotic neural networks and the Hebbian learning rule. The emergence of novel syntax modifying the acquired syntax is demonstrated. This work was presented in part at the 11th International Symposium on Artificial Life and Robotics, Oita, Japan, January 23–25, 2006     

Hippocampal neural network model performing navigation by homing vector field adhesion to sensor map

We propose an artificial neural network model for autonomous agents, i.e., mobile robots, to learn maps of environments and acquire the ability to perform home-navigation autonomously. The networks consists of two subnetworks, each of which has a similar structure with hippocampal lamellar neuronal circuits. Hebbian learning procedures self-organize the first subnetwork to output the distributed sinusoidal activity of the cells by accumulating motor information generated during movement, and the second subnetwork to output localized activity by prototyping sensory information. These patterns represent a homing vector providing the relative coordinates of the agent from a starting point, and a place code corresponding uniquely to a point of the environment. By attaching homing vectors to the sensor map, the homing vector is associated with the sensory stimuli. Then the agents can perform home-navigation autonomously by this association. This work was presented, in part, at the Second International Symposium on Artificial Life and Robotics, Oita, Japan, February 18–20, 1997     

Design of a chaotic neural network for training and retrieval of grayscale and binary patterns

Experimental and theoretical evidence shows that biological system processing behavior has nonlinear and chaotic properties. The ability of emerging various solutions for a problem and the existence of a supervisor to guide this variety to become close to the goal, are the two main properties of a problem solver. In this paper, a chaotic neural network which uses chaotic nodes with the logistic map as activation functions is designed to make the ability of emerging various solutions and an NDRAM is considered as a supervisor to guide these various solutions. The proposed chaotic neural network has better performance in comparison with Hopfield, NDRAM, and L. Zhao et al. ChNN.     

基于混沌神经网络的故障暂态量选线方法研究

为了有效提取故障暂态信息,研究选取适当的小波包基函数。针对电力系统故障暂态量的特点,为了有效克服非故障暂态信号的干扰,研究选取了容错性和联想记忆功能很强的混沌神经网络实现故障选线,并采用改进的遗传算法对混沌神经网络的权值和参数同时进行训练,加快其收敛速度。根据目标模式与神经元的输出状态构造了数值型选线判据。通过实验算例验证了基于暂态量选线判据的有效性和适用性。     

Prediction of a Lorenz chaotic attractor using two-layer perceptron neural network

This paper investigates the prediction of a Lorenz chaotic attractor having relatively high values of Lypunov's exponents. The characteristic of this time series is its rich chaotic behavior. For such dynamic reconstruction problem, regularized radial basis function (RBF) neural network (NN) models have been widely employed in the literature. However, author recommends using a two-layer multi-layer perceptron (MLP) NN-based recurrent model. When none of the available linear models have been able to learn the dynamics of this attractor, it is shown that the proposed NN-based auto regressive (AR) and auto regressive moving average (ARMA) models with regularization have not only learned the true trajectory of this attractor, but also performed much better in multi-step-ahead predictions. However, equivalent linear models seem to fail miserably in learning the dynamics of the time series, despite the low values of Akaike's final prediction error (FPE) estimate. Author proposes to employ the recurrent NN-based ARMA model with regularization which clearly outperforms all other models and thus, it is possible to obtain good results for prediction and reconstruction of the dynamics of the chaotic time series with NN-based models.     

Sequence memory based on an oscillatory neural network

In the brain,the discrete elements in a temporal order is encoded as a sequence memory.At the neural level,the reproducible sequence order of neural activity is very crucial for many cases.In this paper,a mechanism for oscillation in the network has been proposed to realize the sequence memory.The mechanism for oscillation in the network that cooperates with hetero-association can help the network oscillate between the stored patterns,leading to the sequence memory.Due to the oscillatory mechanism,the firing history will not be sampled,the stability of the sequence is increased,and the evolvement of neurons’states only depends on the current states.The simulation results show that neural network can effectively achieve sequence memory with our proposed model.     

基于二重积分定义的神经网络求数值积分方法研究

针对x-型或y-型二重积分的数值计算问题,提出了一种求解二重积分的神经网络模型及学习算法.该方法初始时在积分区域内的两个方向上各自任意选取一定的节点,然后用神经网络来优化网络权值,最后得到比较精确的积分结果.通过3个典型算例,计算机仿真实验结果表明,提出的神经网络算法相比传统的计算二重积分的方法(如:复化Simpson法、复化Trapezium法),具有计算精度较高、收敛速度快等特点.     

基于余弦基神经网络求震荡函数积分方法

针对震荡函数数值积分计算问题,提出了一种基于余弦基函数神经网络模型和学习算法,将该算法应用于求解震荡函数数值积分.通过算例,计算机仿真实验表明,提出的算法相比传统的震荡函数数值积分方法,具有模型简单、计算精度较高、收敛速度快等特点.     

Chaotic neural networks and chaotic annealing

A simple model of single neuron with chaotic dynamics is proposed. Neural networks coupled by such neurons have the property of temporal retrieval of stored patterns in a chaotic way. The network is also studied from the viewpoint of optimization. A chaotic annealing technique is developed to search for the global minima of the energy with transient chaos.     

An artificial neural network noise reduction method for chaotic attractors

A method is presented to reduce noise in chaotic attractors without knowing the underlying maps. The method is based on using Artificial Neural Network (ANN) for moderate levels of additive noise. For high levels of additive noise, a combination of a refinement procedure with ANN is used. In this case, only one refinement is needed for the successful use of ANN. The obtained ANN model is used for long-term predictions of the future behavior of a Henon attractor, using information based only on past values.     

一种小波神经网络的混沌加密算法研究

概括了小波神经网络的主要理论,将小波神经网络和混沌系统相结合,建立了一种混沌序列的生成模型,给出基于小波神经网络的混沌加密算法,最后对算法进行计算机仿真实验.结果表明小波神经网络具有更快的收敛速度和更准确的逼近能力,而基于小波神经网络的混沌加密算法具有很高的安全性.     

基于神经网络的多元特征融合身份识别系统

从信息融合的角度出发,利用神经网络的方法将语音信号、人脸图像等多元特征数据信息有机地结合起来,设计并实现了一种基于神经网络的智能融合身份识别系统。系统利用改进的线性预测和轮廓检测等方法,求出3类特征参数,并将它们进行关联,最后利用RBF人工神经网络进行融合识别。实验表明,与传统的单一特征识别系统相比,该方法具有更好的识别效果。     

Design of controller on synchronization of chaotic neural networks with mixed time-varying delays

In this paper, the problem on synchronization is investigated for neural networks with discrete and distributed time-varying delays as well as generalized activation functions. By constructing proper Lyapunov–Krasovskii functional and employing a combination of the free-weighting matrix method, Newton–Leibniz formulation and inequality technique, the controllers are, respectively, designed to achieve the asymptotical and exponential synchronization of the addressed neural networks. The provided conditions are expressed in terms of LMIs, and are dependent on both the discrete and distributed time delays. A simulation example is given to show the effectiveness and less conservatism of the obtained conditions. It is noteworthy that the traditional assumptions on the differentiability of the time-varying delays and the boundedness of its derivative are removed.     

Anti-synchronization of stochastic perturbed delayed chaotic neural networks

This paper studies the anti-synchronization of a class of stochastic perturbed chaotic delayed neural networks. By employing the Lyapunov functional method combined with the stochastic analysis as well as the feedback control technique, several sufficient conditions are established that guarantee the mean square exponential anti-synchronization of two identical delayed networks with stochastic disturbances. These sufficient conditions, which are expressed in terms of linear matrix inequalities (LMIs), can be solved efficiently by the LMI toolbox in Matlab. Two numerical examples are exploited to demonstrate the feasibility and applicability of the proposed synchronization approaches.     

Global impulsive exponential anti-synchronization of delayed chaotic neural networks

In this paper, the impulsive exponential anti-synchronization for chaotic delayed neural networks is investigated. By establishing an integral delay inequality and using the inequality method, some sufficient conditions ensuring impulsive exponential anti-synchronization of two chaotic delayed networks are derived. To illustrate the effectiveness of the new scheme, a numerical example is given.     

A novel compensation-based recurrent fuzzy neural network and its learning algorithm

Based on detailed study on several kinds of fuzzy neural networks, we propose a novel compensation-based recurrent fuzzy neural network (CRFNN) by adding recurrent element and compensatory element to the conventional fuzzy neural network. Then, we propose a sequential learning method for the structure identification of the CRFNN in order to confirm the fuzzy rules and their correlative parameters effectively. Furthermore, we improve the BP algorithm based on the characteristics of the proposed CRFNN to train the network. By modeling the typical nonlinear systems, we draw the conclusion that the proposed CRFNN has excellent dynamic response and strong learning ability. Supported by the National High-Tech Research and Development Program of China (Grant No. 2006AA05A107) and Special Fund of Jiangsu Province for Technology Transfer (Grant No. BA2007008)     

Supervised extended ART: A fast neural network classifier trained by combining supervised and unsupervised learning

A neural network classifier, called supervised extended ART (SEART), that incorporates a supervised mechanism into the extended unsupervised ART is presented here. It uses a learning theory called Nested Generalized Exemplar (NGE) theory. In any time, the training instances may or may not have desired outputs, that is, this model can handle supervised learning and unsupervised learning simultaneously. The unsupervised component finds the cluster relations of instances, and the supervised component learns the desired associations between clusters and classes. In addition, this model has the ability of incremental learning. It works equally well when instances in a cluster belong to different classes. Also, multi-category and nonconvex classifications can be dealt with. Besides, the experimental results are very encouraging.     

基于Chebyshev正交函数神经网络的混沌系统鲁棒自适应同步

提出了基于Chebyshev正交函数神经网络的不确定性混沌系统的鲁棒自适应同步方法.首先,本文提出了正交函数神经网络的网络结构,分析了利用Chebyshev正交多项式形成神经网络的机理.利用Lyapunov稳定性定理确定正交函数神经网络控制器的权值更新规则,并保证权值误差和跟踪误差的有界性.该方法能克服不确定性对混沌系统同步的破坏,实现了良好的同步效果.在本文最后,针对Lorenz系统进行了数值计算,数值计算结果表明了所给方法的有效性.     

Efficient neural chaotic generator for image encryption

In this paper, we propose a new implementation of chaotic generator using artificial neural network. Neural network can act as an efficient source of perturbation in the chaotic generator which increases the cycleʼs length, and thus avoid the dynamical degradation due to the used finite dimensional space. On the other hand, the use of neural network enlarges the key space of the chaotic generator in an enormous way. The efficiency of the proposed neural chaotic generator is illustrated using some dynamical and NIST statistical tests. We also propose in this paper, a new image encryption method based on chaotic sequence, and the obtained results emphasize the efficiency of our technique.     

局部递归神经网络控制器及其应用

基于人工神经网络提出了一种局部递归神经网络控制器。在描述了带有输出反馈和激活反馈的网络控制器的结构组成并定义了作为设计目标的误差函数后,采用带有弹性的梯度下降法,获得适用于实时在线调整权值的修正公式,给出了所提的网络控制器的设计步骤及其控制策略。将所提出的网络控制器应用到典型的单级倒立摆的实验系统中,将实验所获得的结果与LQY方法的实验结果进行了对比。