A study on the use of statistical tests for experimentation with neural networks: Analysis of parametric test conditions and non-parametric tests

In this paper, we focus on the experimental analysis on the performance in artificial neural networks with the use of statistical tests on the classification task. Particularly, we have studied whether the sample of results from multiple trials obtained by conventional artificial neural networks and support vector machines checks the necessary conditions for being analyzed through parametrical tests. The study is conducted by considering three possibilities on classification experiments: random variation in the selection of test data, the selection of training data and internal randomness in the learning algorithm.The results obtained state that the fulfillment of these conditions are problem-dependent and indefinite, which justifies the need of using non-parametric statistics in the experimental analysis.     

Job-shop排序问题的遗传强化学习算法

针对Job-shop排序问题的复杂性,提出一种遗传强化学习算法对其求解。通过引入多个随机变量,把Job-shop排序问题转换成多阶段决策问题,通过仿真手段构建作业排序问题模型环境,求取系统性能指标并保证解的可行性。设计一个多智能体Q-Learning算法和遗传算法相结合的算法用于解决Job-shop排序问题。仿真优化实验结果验证了该算法的有效性。     

一种基于受限约束范围标签传播的半监督学习算法

提出一种基于受限约束范围标签传播的半监督学习算法。首先利用相似性矩阵计算得出概率转移矩阵,进而通过概率转移矩阵得出受限约束范围。然后在约束范围内利用半监督学习框架下的标签传播算法计算基于路径的相似性,路径相似性决定了标签传播的重要路径。由于只使用几条重要的传播路径使得算法中省去计算每一条路径的相似度,计算复杂度大大减少。最终使得标签在带标签数据与未标签数据之间通过几条重要的路径之间传播。实验已经证明此算法的有效性。     

深度学习应用技术研究

本文针对深度学习应用技术进行了研究性综述。详细阐述了RBM（Restricted Boltzmann Machine）逐层预训练后再用BP（back-propagation）微调的深度学习贪婪层训练方法,对比分析了BP算法中三种梯度下降的方式,建议在线学习系统,采用随机梯度下降,静态离线学习系统采用随机小批量梯度下降;归纳总结了深度学习深层结构特征,并推荐了目前最受欢迎的5层深度网络结构设计方法。分析了前馈神经网络非线性激活函数的必要性及常用的激活函数优点,并推荐ReLU （rectified linear units）激活函数。最后简要概括了深度CNNs(Convolutional Neural Networks), 深度RNNs(recurrent neural networks), LSTM(long short-termmemory networks)等新型深度网络的特点及应用场景,并归纳总结了当前深度学习可能的发展方向。     

A new expert system for learning management systems evaluation based on neutrosophic sets

There has been a sudden increase in the usage of Learning Management Systems applications to support learner's learning process in higher education. Many studies in learning management system evaluation are implemented under complete information, while the real environment has uncertainty aspects. As these systems were described by development organizations with uncertainty terms such as vague, imprecise, ambiguity and inconsistent, that is why traditional evaluation methods may not be effective. This paper suggests neutrosophic logic as a better option to simulate human thinking than fuzzy logic because unlike fuzzy logic, it is able to handle indeterminacy of information which expresses the percentage of unknown parameters. As previous studies suggested neutrosophic decision maker and neutrosophic expert systems as future work in ecommerce and e‐learning applications, this paper presents neutrosphic expert system for learning management systems evaluation. Information for building and validating the neutrosophic expert system is collected from five experts using surveys, and then analysis is done by using Fuzzytech 5.54d software. Finally, the comparison between fuzzy expert system and neutrosophic expert system results show that the neutrosophic logic is capable of representing uncertainty in human thinking for evaluating Learning Management Systems.     

基函数可递归的泛函神经元网络学习算法

将泛函神经元结构做了一个变形,给出了一种基函数可递归的泛函神经元网络学习算法,该算法借助于矩阵伪逆递归求解方法,完成对泛函神经元网络基函数的自适应调整,最终实现泛函网络结构和参数共同的最优求解。数值仿真实验结果表明,该算法具有自适应性、鲁棒性和较高的收敛精度,将在实时在线辨识中有着广泛的应用。     

K Nearest Neighbor Equality: Giving equal chance to all existing classes

The nearest neighbor classification method assigns an unclassified point to the class of the nearest case of a set of previously classified points. This rule is independent of the underlying joint distribution of the sample points and their classifications. An extension to this approach is the k-NN method, in which the classification of the unclassified point is made by following a voting criteria within the k nearest points.The method we present here extends the k-NN idea, searching in each class for the k nearest points to the unclassified point, and classifying it in the class which minimizes the mean distance between the unclassified point and the k nearest points within each class. As all classes can take part in the final selection process, we have called the new approach k Nearest Neighbor Equality (k-NNE).Experimental results we obtained empirically show the suitability of the k-NNE algorithm, and its effectiveness suggests that it could be added to the current list of distance based classifiers.     

Learning effective color features for content based image retrieval in dermatology

We investigate the extraction of effective color features for a content-based image retrieval (CBIR) application in dermatology. Effectiveness is measured by the rate of correct retrieval of images from four color classes of skin lesions. We employ and compare two different methods to learn favorable feature representations for this special application: limited rank matrix learning vector quantization (LiRaM LVQ) and a Large Margin Nearest Neighbor (LMNN) approach. Both methods use labeled training data and provide a discriminant linear transformation of the original features, potentially to a lower dimensional space. The extracted color features are used to retrieve images from a database by a k-nearest neighbor search. We perform a comparison of retrieval rates achieved with extracted and original features for eight different standard color spaces. We achieved significant improvements in every examined color space. The increase of the mean correct retrieval rate lies between 10% and 27% in the range of k=1-25 retrieved images, and the correct retrieval rate lies between 84% and 64%. We present explicit combinations of RGB and CIE-Lab color features corresponding to healthy and lesion skin. LiRaM LVQ and the computationally more expensive LMNN give comparable results for large values of the method parameter κ of LMNN (κ≥25) while LiRaM LVQ outperforms LMNN for smaller values of κ. We conclude that feature extraction by LiRaM LVQ leads to considerable improvement in color-based retrieval of dermatologic images.     

Training linear ranking SVMs in linearithmic time using red-black trees

We introduce an efficient method for training the linear ranking support vector machine. The method combines cutting plane optimization with red-black tree based approach to subgradient calculations, and has O(ms + mlog (m)) time complexity, where m is the number of training examples, and s the average number of non-zero features per example. Best previously known training algorithms achieve the same efficiency only for restricted special cases, whereas the proposed approach allows any real valued utility scores in the training data. Experiments demonstrate the superior scalability of the proposed approach, when compared to the fastest existing RankSVM implementations.