Negative correlation in incremental learning

Negative Correlation Learning (NCL) has been successfully applied to construct neural network ensembles. It encourages the neural networks that compose the ensemble to be different from each other and, at the same time, accurate. The difference among the neural networks that compose an ensemble is a desirable feature to perform incremental learning, for some of the neural networks can be able to adapt faster and better to new data than the others. So, NCL is a potentially powerful approach to incremental learning. With this in mind, this paper presents an analysis of NCL, aiming at determining its weak and strong points to incremental learning. The analysis shows that it is possible to use NCL to overcome catastrophic forgetting, an important problem related to incremental learning. However, when catastrophic forgetting is very low, no advantage of using more than one neural network of the ensemble to learn new data is taken and the test error is high. When all the neural networks are used to learn new data, some of them can indeed adapt better than the others, but a higher catastrophic forgetting is obtained. In this way, it is important to find a trade-off between overcoming catastrophic forgetting and using an entire ensemble to learn new data. The NCL results are comparable with other approaches which were specifically designed to incremental learning. Thus, the study presented in this work reveals encouraging results with negative correlation in incremental learning, showing that NCL is a promising approach to incremental learning.

基于人工神经网络的负相关学习研究

人工神经网络集成技术是神经计算技术的一个研究热点,在许多领域中已经有了成熟的应用.神经网络集成是用有限个神经网络对同一个问题进行学习,集成在某输入示例下的输出由构成集成的各神经网络在该示例下的输出共同决定.负相关学习法是一种神经网络集成的训练方法,它鼓励集成中的不同个体网络学习训练集的不同部分,以使整个集成能更好地学习整个训练数据.改进的负相关学习法是在误差函数中使用一个带冲量的BP算法,给合了原始负相关学习法和带冲量的BP算法的优点,使改进的算法成为泛化能力强、学习速度快的批量学习算法.     

A survey on ensemble learning

Despite significant successes achieved in knowledge discovery,traditional machine learning methods may fail to obtain satisfactory performances when dealing with complex data,such as imbalanced,high-dimensional,noisy data,etc.The reason behind is that it is difficult for these methods to capture multiple characteristics and underlying structure of data.In this context,it becomes an important topic in the data mining field that how to effectively construct an efficient knowledge discovery and mining model.Ensemble learning,as one research hot spot,aims to integrate data fusion,data modeling,and data mining into a unified framework.Specifically,ensemble learning firstly extracts a set of features with a variety of transformations.Based on these learned features,multiple learning algorithms are utilized to produce weak predictive results.Finally,ensemble learning fuses the informative knowledge from the above results obtained to achieve knowledge discovery and better predictive performance via voting schemes in an adaptive way.In this paper,we review the research progress of the mainstream approaches of ensemble learning and classify them based on different characteristics.In addition,we present challenges and possible research directions for each mainstream approach of ensemble learning,and we also give an extra introduction for the combination of ensemble learning with other machine learning hot spots such as deep learning,reinforcement learning,etc.     

一种基于Bagging-SVM的智能传感器集成学习方法

集成多个传感器的智能片上系统( SoC)在物联网得到了广泛的应用.在融合多个传感器数据的分类算法方面,传统的支持向量机( SVM)单分类器不能直接对传感器数据流进行小样本增量学习.针对上述问题,提出一种基于Bagging-SVM的集成增量算法,该算法通过在增量数据中采用Bootstrap方式抽取训练集,构造能够反映新信息变化的集成分类器,然后将新老分类器集成,实现集成增量学习.实验结果表明:该算法相比SVM单分类器能够有效降低分类误差,提高分类准确率,且具有较好的泛化能力,可以满足当下智能传感器系统基于小样本数据流的在线学习需求.     

监督与半监督学习下的数据流集成分类综述

在监督或半监督学习的条件下对数据流集成分类进行研究是一个很有意义的方向.从基分类器、关键技术、集成策略等三个方面进行介绍,其中,基分类器主要介绍了决策树、神经网络、支持向量机等;关键技术从增量、在线等方面介绍;集成策略主要介绍了boosting、stacking等.对不同集成方法的优缺点、对比算法和实验数据集进行了总结与分析.最后给出了进一步研究方向,包括监督和半监督学习下对于概念漂移的处理、对于同质集成和异质集成的研究,无监督学习下的数据流集成分类等.     

Multi-armed bandit heterogeneous ensemble learning for imbalanced data

One of the most widely used approaches to the class-imbalanced issue is ensemble learning. The base classifier is trained using an unbalanced training set in the conventional ensemble learning approach. We are unable to select the best suitable resampling method or base classifier for the training set, despite the fact that researchers have examined employing resampling strategies to balance the training set. A multi-armed bandit heterogeneous ensemble framework was developed as a solution to these issues. This framework employs the multi-armed bandit technique to pick the best base classifier and resampling techniques to build a heterogeneous ensemble model. To obtain training sets, we first employ the bagging technique. Then, we use the instances from the out-of-bag set as the validation set. In general, we consider the basic classifier combination with the highest validation set score to be the best model on the bagging subset and add it to the pool of model. The classification performance of the multi-armed bandit heterogeneous ensemble model is then assessed using 30 real-world imbalanced data sets that were gathered from UCI, KEEL, and HDDT. The experimental results demonstrate that, under the two assessment metrics of AUC and Kappa, the proposed heterogeneous ensemble model performs competitively with other nine state-of-the-art ensemble learning methods. At the same time, the findings of the experiment are confirmed by the statistical findings of the Friedman test and Holm's post-hoc test.     

基于集成学习的口令强度评估模型

针对现有的口令评估模型通用性差,没有一个可以对从简单口令到非常复杂口令都适用的评估模型的问题,设计了一种基于多模型的集成学习的口令评估模型。首先,使用真实的口令训练集训练多个现有的口令评估模型作为子模型;其次,将多个经过训练的子模型作为基学习器进行集成学习,采用偏弱项投票法的结合策略实现各个子模型的优势集成;最后,实现一个以高准确性为前提的通用口令评估模型。实验中使用网络泄露的真实用户口令数据集作为实验数据,实验结果表明,基于多模型集成学习模型针对不同复杂程度的口令进行口令强度评估,其评估结果准确率高、通用性强,所提模型在口令评估方面具有较好的适用性。     

基于异构分类器集成的增量学习算法

将集成学习的思想引入到增量学习之中可以显著提升学习效果,近年关于集成式增量学习的研究大多采用加权投票的方式将多个同质分类器进行结合,并没有很好地解决增量学习中的稳定-可塑性难题。针对此提出了一种异构分类器集成增量学习算法。该算法在训练过程中,为使模型更具稳定性,用新数据训练多个基分类器加入到异构的集成模型之中,同时采用局部敏感哈希表保存数据梗概以备待测样本近邻的查找;为了适应不断变化的数据,还会用新获得的数据更新集成模型中基分类器的投票权重;对待测样本进行类别预测时,以局部敏感哈希表中与待测样本相似的数据作为桥梁,计算基分类器针对该待测样本的动态权重,结合多个基分类器的投票权重和动态权重判定待测样本所属类别。通过对比实验,证明了该增量算法有比较高的稳定性和泛化能力。     

基于散度的网络流概念漂移分类方法

网络流量特征分布的动态变化产生概念漂移问题,造成基于机器学习的网络流量分类模型精度下降.定期更新分类模型耗时且无法保证分类模型的泛化能力.基于此,提出一种基于散度的网络流概念漂移分类方法(ensemble classification based on divergence detection, ECDD),采用双层窗口机制,从信息熵的角度出发,根据流量特征分布的JS散度,记为JSD(Jensen-Shannon divergence)来度量滑动窗口内数据分布的差异,从而检测概念漂移.借鉴增量集成学习的思想,检测到漂移时对于新样本重新训练出新的分类器,之后通过分类器权值排序,保留性能较高的分类器,加权集成分类结果对样本进行分类.抓取常见的网络应用流量,根据应用特征分布的不同构建概念漂移数据集,将该方法与常见的概念漂移检测方法进行实验对比,实验结果表明：该方法可以有效地检测概念漂移和更新分类器,表现出较好的分类性能.     

聚类的动态分类器集成选择

动态分类器集成选择(DCES)是当前集成学习领域中一个非常重要的研究方向。然而,当前大部分 DCES算法的计算复杂度较高。为了解决该问题和进一步提高算法的性能,本文提出了基于聚类的动态分类器集成选择(CDCES),该方法通过对测试样本聚类,极大地减少了动态选择分类器的次数,因而降低了算法的计算复杂度。同时, CDCES是一种更加通用的算法,传统的静态选择性集成和动态分类器集成为本算法的特殊情况,因而本算法是一种鲁棒性更强的算法。通过对UCI数据集进行测试,以及与其他算法作比较,说明本算法是一种有效的、计算复杂度较低的方法。     

一种基于聚类技术的选择性神经网络集成方法

神经网络集成是一种很流行的学习方法,通过组合每个神经网络的输出生成最后的预测.为 了提高集成方法的有效性,不仅要求集成中的个体神经网络具有很高的正确率,而且要求这 些网络在输入空间产生不相关的错误.然而,在现有的众多集成方法中,大都采用将训练的 所有神经网络直接进行组合以形成集成,实际上生成的这些神经网络可能具有一定的相关性 .为了进一步提高神经网络间的差异性,一种基于聚类技术的选择性神经网络集成方法CLU_E NN被提出.在获得个体神经网络后,并不直接对这些神经网络集成,而是先应用聚类算法对 这些神经网络模型聚类以获得差异较大的部分神经网络;然后由部分神经网络构成集成;最 后,通过实验研究了CLU_ENN集成方法,与传统的集成方法Bagging相比,该方法取得了更好 的效果.     

Cluster‐based ensemble of classifiers

This paper presents cluster‐based ensemble classifier – an approach toward generating ensemble of classifiers using multiple clusters within classified data. Clustering is incorporated to partition data set into multiple clusters of highly correlated data that are difficult to separate otherwise and different base classifiers are used to learn class boundaries within the clusters. As the different base classifiers engage on different difficult‐to‐classify subsets of the data, the learning of the base classifiers is more focussed and accurate. A selection rather than fusion approach achieves the final verdict on patterns of unknown classes. The impact of clustering on the learning parameters and accuracy of a number of learning algorithms including neural network, support vector machine, decision tree and k‐NN classifier is investigated. A number of benchmark data sets from the UCI machine learning repository were used to evaluate the cluster‐based ensemble classifier and the experimental results demonstrate its superiority over bagging and boosting.     

An incremental neural learning framework and its application to vehicle diagnostics

This paper presents a framework for incremental neural learning (INL) that allows a base neural learning system to incrementally learn new knowledge from only new data without forgetting the existing knowledge. Upon subsequent encounters of new data examples, INL utilizes prior knowledge to direct its incremental learning. A number of critical issues are addressed including when to make the system learn new knowledge, how to learn new knowledge without forgetting existing knowledge, how to perform inference using both the existing and the newly learnt knowledge, and how to detect and deal with aged learnt systems. To validate the proposed INL framework, we use backpropagation (BP) as a base learner and a multi-layer neural network as a base intelligent system. INL has several advantages over existing incremental algorithms: it can be applied to a broad range of neural network systems beyond the BP trained neural networks; it retains the existing neural network structures and weights even during incremental learning; the neural network committees generated by INL do not interact with one another and each sees the same inputs and error signals at the same time; this limited communication makes the INL architecture attractive for parallel implementation. We have applied INL to two vehicle fault diagnostics problems: end-of-line test in auto assembly plants and onboard vehicle misfire detection. These experimental results demonstrate that the INL framework has the capability to successfully perform incremental learning from unbalanced and noisy data. In order to show the general capabilities of INL, we also applied INL to three general machine learning benchmark data sets. The INL systems showed good generalization capabilities in comparison with other well known machine learning algorithms.     

An OS-ELM based distributed ensemble classification framework in P2P networks

Although classification in centralized environments has been widely studied in recent years, it is still an important research problem for classification in P2P networks due to the popularity of P2P computing environments. The main target of classification in P2P networks is how to efficiently decrease prediction error with small network overhead. In this paper, we propose an OS-ELM based ensemble classification framework for distributed classification in a hierarchical P2P network. In the framework, we apply the incremental learning principle of OS-ELM to the hierarchical P2P network to generate an ensemble classifier. There are two kinds of implementation methods of the ensemble classifier in the P2P network, one-by-one ensemble classification and parallel ensemble classification. Furthermore, we propose a data space coverage based peer selection approach to reduce high the communication cost and large delay. We also design a two-layer index structure to efficiently support peer selection. A peer creates a local Quad-tree to index its local data and a super-peer creates a global Quad-tree to summarize its local indexes. Extensive experimental studies verify the efficiency and effectiveness of the proposed algorithms.     

Feature-based ensemble learning for hyperspectral chemical plume detection

Feature-based ensemble learning, where weak hypotheses are learned within the associated feature subspaces constructed by repeated random feature selection, is described. The proposed ensemble approach is less affected by noisy features or outliers unique to the training set than the bagging and boosting algorithms due to the randomized selection of feature subsets from the entire training set. The individual weak hypotheses perform their own generalization processes, within the associated feature subspaces, independently of each other. This allows the proposed ensemble to provide improved performance on unseen data over other ensemble learning methods that randomly choose subsets of training samples in an input space. The weak hypotheses are combined through three different aggregating strategies: majority voting, weighted average and neural network-based aggregation. The proposed ensemble technique has been applied to hyperspectral chemical plume data and a performance comparison of the proposed and other existing ensemble methods is presented.     

一种新的决策树选择性集成学习方法

个体学习器的差异度是集成学习中的关键因素。流行的集成学习算法如Bagging通过重取样技术产生个体学习器的差异度。选择性集成从集成学习算法产生的个体学习器中选择一部分来集成,结果表明比原集成更好。但如何选择学习器是个难题。使用Q统计量度量两个学习器的差异度,提出一种新的决策树选择性集成学习方法。与C4.5,Bagging方法相比,表现出很好的效果。     

自适应嵌套级联的在线集成学习方法研究

针对视频目标检测问题,提出一种新的在线集成学习方法。该方法把目标检测看成两类分类问题,首先用少量已标注样本离线训练一个初始集成分类器,然后在检测目标的同时通过跟踪过滤虚警目标,并通过样本置信度作进一步验证自动标注样本,最后通过在线集成学习方法更新级联分类器。该方法通过在线调整级联分类器,提高分类器对目标环境变化的适应能力,在大量视频序列上进行实验验证,并与现有在线集成学习方法进行比较,结果表明,通过该方法训练得到的检测器不但能够很好地应对目标特征的变化,也能在出现目标遮挡及背景干扰下稳定地检测出目标,具有较好的适应性及鲁棒性。     

基于集成学习的Self-training在入侵检测中的应用

针对入侵检测的标记数据难以获得的问题,提出一种基于集成学习的Self-training方法——正则化Self-training。该方法结合主动学习和正则化理论,利用无标记数据对已有的分类器（该分类器对分类模式已学习得很好）作进一步的改进。对三种主要的集成学习方法在不同标记数据比例下进行对比实验,实验结果表明：借助大量无标记数据可以改善组合分类器的分类边界,算法能显著地降低结果分类器的错误率。     

基于多机器学习竞争策略的短时雷电预报

传统的雷电数据预测方法往往采用单一最优机器学习算法,较少考虑气象数据的时空变化等现象。针对该现象,提出一种基于集成策略的多机器学习短时雷电预报算法。首先,对气象数据进行属性约简,降低数据维度;其次,在数据集上训练多种异构机器学习分类器,并基于预测质量筛选最优基分类器;最后,通过对最优基分类器训练权重,并结合集成策略产生最终分类器。实验表明,该方法优于传统单最优方法,其平均预测准确率提高了9.5%。     

基于相关性分析的瓦斯灾害选择集成预测模型

针对瓦斯灾害危险性预测中预测性能低的问题，对一种基于矿井内瓦斯浓度与环境因素相关性分析的瓦斯灾害选择集成预测方法进行了研究。首先，分析实验数据中样本属性与瓦斯浓度的相关性，并根据相关性分析结果进行属性约简得到新的数据集；其次，训练基学习器并应用优化集成前序选择方法建立选择集成回归学习模型；最后，将模型应用于瓦斯灾害预测。实验结果表明，基于相关性分析的选择集成回归学习模型对瓦斯灾害危险性的识别率比未进行相关性分析的四个基学习器平均提高了24%，比未进行相关性分析的选择集成回归学习模型提高了7.6%。