Hopfield神经网络参数设置

以TSP问题入手,详细分析了Hopfield神经网络行为特征。采用了加强能量函数,比H-T模式更有效。从几何学角度分析了权值矩阵的特征值所对应的子空间,从而获得设置网络参数的标准。模拟结果显示,新的网络参数能保证网络收敛到有效解。     

利用进化规划设计人工神经网络

近年来,人们开发了许多的神经网络自动设计方法,其中进化算法与神经网络的结合最引人注目,形成一类进化人工神经网络。对用遗传算法实现神经网络的进化进行研究的时间最早,并得到广泛的评论,而最近越来越多的研究支持利用进化规划设计神经网络是一种更优的方法。该文讨论了这一领域的研究进展并阐明了进一步的研究方向。     

Modelling Temporal Series Through Synaptic Delay-based Neural Networks

In this paper we address the problem of the dynamic reconstruction of chaotic time series using a new training algorithm for delay-based neural networks, where the delays can be trained. In signal reconstruction terms, trainable delay-based Artificial Neural Networks (ANN) directly implement a form of the embedding theorem, and the training algorithm we have developed for this particular type of networks implicitly and autonomously obtains the embedding dimension and the normalised embedding delay. This structure and training algorithm permit training neural networks for temporal reasoning without resorting to any explicit time windowing process or determining parameters of the signal, such as the best dimension for the state space in which to unambiguously represent its evolution orthe appropriate sampling rate. In this work, the capacity of the neural network and training algorithm in the modeling of time series is tested in the prediction of future values of chaotic time series using iterative multistep prediction. Finally, to provide some indication of the real world operation of these types of systems in the reconstruction of signals, we present some results obtained in the prediction of hot wire anemometer measurements of the velocity of a turbulent flow in a Karman Vortex Street, which is a difficult problem in fluid dynamics.     

Deterministic Learning for Maximum-Likelihood Estimation Through Neural Networks

In this paper, a general method for the numerical solution of maximum-likelihood estimation (MLE) problems is presented; it adopts the deterministic learning (DL) approach to find close approximations to ML estimator functions for the unknown parameters of any given density. The method relies on the choice of a proper neural network and on the deterministic generation of samples of observations of the likelihood function, thus avoiding the problem of generating samples with the unknown density. Under mild assumptions, consistency and convergence with favorable rates to the true ML estimator function can be proved. Simulation results are provided to show the good behavior of the algorithm compared to the corresponding exact solutions.      

Fusing Neural Networks Through Space Partitioning and Fuzzy Integration

To improve recognition results, decisions of multiple neural networks can be aggregated into a committee decision. Aggregation weights assigned to neural networks or groups of networks can be the same in the entire data space or can be different (data dependent) in various regions of the space. In this paper, we propose a method for obtaining data dependent aggregation weights. The proposed approach is tested in two aggregation schemes, namely aggregation through neural network selection, and aggregation by the Choquet integral with respect to the -fuzzy measure. The effectiveness of the approach is demonstrated on two artificial and three real data sets.     

基于模糊加权神经网络的模糊规则自动获取

如何实现模糊规则的自动获取一直是模糊系统中的一个难题，文中在充分研究了模糊加权神经网络和遗传算法的基础上，给出了一种能够自动获取模糊规则的剪枝算法，并以此建立了新的网络模型。模拟结果验证了该模型的有效性。     

人工神经网络在造纸工业自动控制中的应用

针对造纸工业传统控制中存在精确度低的问题,提出了利用人工神经网络进行预测控制的方法。通过人工神经网络在造纸工业的应用实例介绍,显示出人工神经网络是一种有效的智能控制手段,在自动控制上具有巨大优势。文章最后还对人工神经网络的应用与研究发展前景进行了评价。     

Automatic Tumor Segmentation with Deep Convolutional Neural Networks for Radiotherapy Applications

Accurate tumor delineation in medical images is of great importance in guiding radiotherapy. In nasopharyngeal carcinoma (NPC), due to its high variability, low contrast and discontinuous boundaries in magnetic resonance images (MRI), the margin of the tumor is especially difficult to be identified, making the radiotherapy planning a more challenging problem. The objective of this paper is to develop an automatic segmentation method of NPC in MRI for radiosurgery applications. To this end, we present to segment NPC using a deep convolutional neural network. Specifically, to obtain spatial consistency as well as accurate feature details for segmentation, multiple convolution kernel sizes are employed. The network contains a large number of trainable parameters which capture the relationship between the MRI intensity images and the corresponding label maps. When trained on subjects with pre-labeled MRI, the network can estimate the label class of each voxel for the testing subject which is only given the intensity image. To demonstrate the segmentation performance, we carry on our method on the T1-weighted images of 15 NPC patients, and compare the segmentation results against the radiologist’s reference outline. Experimental results show that the proposed method outperforms the traditional hand-crafted features based segmentation methods. The presented method in this paper could be useful for NPC diagnosis and helpful for guiding radiotherapy.     

基于神经网络的软件无线电信号的调制识别

对接收信号的调制类型进行自动识别,对于软件无线电这类多模式通信系统非常重要。它使得系统可以自动切换到合适的软件解调程序,从而能使系统更具灵活性和适应能力。提出了一种基于神经网络方法的分类算法来解决此问题。实验结果表明,在信噪比为5db时,正确的识别率不低于98％。     

神经网络控制结构及所用神经网络

本文阐述了神经网络控制所能解决的控制难题,若干种控制结构及常用的动态神经网络。讨论了神经网络控制研究的重点,在实时控制中的物理可实现性及其发展等问题。     

Novel Approaches to Probabilistic Neural Networks Through Bagging and Evolutionary Estimating of Prior Probabilities

In this contribution, novel approaches are proposed for the improvement of the performance of Probabilistic Neural Networks as well as the recently proposed Evolutionary Probabilistic Neural Networks. The Evolutionary Probabilistic Neural Network’s matrix of spread parameters is allowed to have different values in each class of neurons, resulting in a more flexible model that fits the data better and Particle Swarm Optimization is also employed for the estimation of the Probabilistic Neural Networks’s prior probabilities of each class. Moreover, the bagging technique is used to create an ensemble of Evolutionary Probabilistic Neural Networks in order to further improve the model’s performance. The above approaches have been applied to several well-known and widely used benchmark problems with promising results.      

Learners Reliability Estimated Through Neural Networks Applied to Build a Novel Hybrid Ensemble Method

Dimensionality reduction (DR) has been one central research topic in information theory, pattern recognition, and machine learning. Apparently, the performance of many learning models significantly rely on dimensionality reduction: successful DR can largely improve various approaches in clustering and classification, while inappropriate DR may deteriorate the systems. When applied on high-dimensional data, some existing research approaches often try to reduce the dimensionality first, and then input the reduced features to other available models, e.g., Gaussian mixture model (GMM). Such independent learning could however significantly limit the performance, since the optimal subspace given by a particular DR approach may not be appropriate for the following model. In this paper, we focus on investigating how unsupervised dimensionality reduction could be performed together with GMM and if such joint learning could lead to improvement in comparison with the traditional unsupervised method. In particular, we engage the mixture of factor analyzers with the assumption that a common factor loading exists for all the components. Based on that, we then present EM-algorithm that converges to a local optimal solution. Such setting exactly optimizes a dimensionality reduction together with the parameters of GMM. We describe the framework, detail the algorithm, and conduct a series of experiments to validate the effectiveness of our proposed approach. Specifically, we compare the proposed joint learning approach with two competitive algorithms on one synthetic and six real data sets. Experimental results show that the joint learning significantly outperforms the comparison methods in terms of three criteria.     

基于循环和卷积神经网络的文本分类研究

文本表示是自然语言处理的基础工作,好的文本表示方法对文本分类等自然语言处理任务的性能起着决定性作用。本文描述了一个结合了循环网络和卷积网络的文本表示和分类网络模型。在该模型中,我们使用词向量作为输入,用循环网络对文档进行表示,然后采用卷积网络对文档进行有效的特征提取,再采用Softmax回归分类。循环网络能够捕捉到文档的中词序信息,而卷积网络能够很好的提取出有用的特征。我们在六个文本分类任务中测试本文所描述的网络模型,都取得了比先前的方法更出色的性能。     

Granular Neural Networks and Their Development Through Context-Based Clustering and Adjustable Dimensionality of Receptive Fields

In this study, we present a new architecture of a granular neural network and provide a comprehensive design methodology as well as elaborate on an algorithmic setup supporting its development. The proposed neural network relates to a broad category of radial basis function neural networks (RBFNNs) in the sense that its topology involves a collection of receptive fields. In contrast to the standard architectures encountered in RBFNNs, here we form individual receptive fields in subspaces of the original input space rather than in the entire input space. These subspaces could be different for different receptive fields. The architecture of the network is fully reflective of the structure encountered in the training data which are granulated with the aid of clustering techniques. More specifically, the output space is granulated with use of K-means clustering while the information granules in the multidimensional input space are formed by using the so-called context-based fuzzy C-means, which takes into account the structure being already formed in the output space. The innovative development facet of the network involves a dynamic reduction of dimensionality of the input space in which the information granules are formed in the subspace of the overall input space which is formed by selecting a suitable subset of input variables so that this subspace retains the structure of the entire space. As this search is of combinatorial character, we use the technique of genetic optimization [genetic algorithms (GAs), to be more specific] to determine the optimal input subspaces. A series of numeric studies exploiting synthetic data and data coming from the Machine Learning Repository, University of California at Irvine, provide a detailed insight into the nature of the algorithm and its parameters as well as offer some comparative analysis.     

Segmented-Memory Recurrent Neural Networks

Conventional recurrent neural networks (RNNs) have difficulties in learning long-term dependencies. To tackle this problem, we propose an architecture called segmented-memory recurrent neural network (SMRNN). A symbolic sequence is broken into segments and then presented as inputs to the SMRNN one symbol per cycle. The SMRNN uses separate internal states to store symbol-level context, as well as segment-level context. The symbol-level context is updated for each symbol presented for input. The segment-level context is updated after each segment. The SMRNN is trained using an extended real-time recurrent learning algorithm. We test the performance of SMRNN on the information latching problem, the “two-sequence problem” and the problem of protein secondary structure (PSS) prediction. Our implementation results indicate that SMRNN performs better on long-term dependency problems than conventional RNNs. Besides, we also theoretically analyze how the segmented memory of SMRNN helps learning long-term temporal dependencies and study the impact of the segment length.      

Evolving Fault-Tolerant Neural Networks

In this paper, genetic algorithm is used to help improve the tolerance of feedforward neural networks against an open fault. The proposed method does not explicitly add any redundancy to the network, nor does it modify the training algorithm. Experiments show that it may profit the fault tolerance as well as the generalisation ability of neural networks.     

复交替投影神经网络

首先对ＭarksII等人提出的交替投影神经网络进行了研究,将其应用范围从实数域拓广到复数域,并证明了其稳态收敛性,接着研究了复数域的中替投影神经网络（不妨称此情形下的网络为复交替投影响神经网络）,得到了几个有用结论,并从数学上对这些结构进行了严格证明,最后,为了验证文中物理分析的正确性,设计了一个仿真实验,仿真实验结果表明文中的理论与验结果完全吻合,实际上,复交替投影神秒仅可用于信号处理中的带限信号外推,还可用于选频,陷波等场合。     

Restricted Convolutional Neural Networks

Neural Processing Letters - In this paper, a new type of convolutional neural network is proposed which is inspired by cellular automata research. This model is referred to as “restricted...