量子机器学习

人工智能和量子物理是上世纪发展起来的两个截然不同但又影响深远的学科.近年来,它们在数据科学方面的结合引起了学术界的高度关注,形成了量子机器学习这个新兴领域.利用量子态的叠加性,量子机器学习有望通过量子并行解决目前机器学习中数据量大,训练过程慢的困难,并有望从量子物理的角度提出新的学习模型.目前该领域的研究还处于探索阶段,涵盖内容虽然广泛,但还缺乏系统的梳理.本文将从数据和算法角度总结量子机器学习与经典机器学习的不同,以及其中涉及的关键加速技巧,针对数据结构(数字型、模拟型),计算技巧(相位估计、Grover搜索、内积计算),基础算法(求解线性系统、主成分分析、梯度算法),学习模型(支持向量机、近邻法、感知器、玻尔兹曼机)等4个方面对现有研究成果进行综述,并建议一些可能的研究方向,供本领域的研究人员参考.     

基于被动-主动的特征演化流学习

在现实应用中,数据通常以流的形式不断积聚,数据的特征可能随时间而演变. 例如,在环境监测任务中,由于旧传感器达到使用寿命和新传感器的部署,数据特征可能会动态地消失或增加. 此外,除了可演变的特征空间,数据标记可能存在噪声. 当特征空间演变和数据标记带噪同时发生时,设计具有理论保障的学习算法,尤其是具备对算法泛化能力的理解是非常具有挑战性的. 为了应对这一挑战,提出了一种在特征演变环境中针对标记带噪数据的差异度量方法,称为容忍标记噪声的演变差异. 该差异度量启发了泛化误差分析,并根据泛化误差的理论分析设计了一种基于深度神经网络实现的学习算法. 合成数据上的实证研究验证了所提差异度量的合理性,而在现实应用任务上的实验则验证了所提算法的有效性.

     

From machine learning to machine reasoning

A plausible definition of “reasoning” could be “algebraically manipulating previously acquired knowledge in order to answer a new question”. This definition covers first-order logical inference or probabilistic inference. It also includes much simpler manipulations commonly used to build large learning systems. For instance, we can build an optical character recognition system by first training a character segmenter, an isolated character recognizer, and a language model, using appropriate labelled training sets. Adequately concatenating these modules and fine tuning the resulting system can be viewed as an algebraic operation in a space of models. The resulting model answers a new question, that is, converting the image of a text page into a computer readable text. This observation suggests a conceptual continuity between algebraically rich inference systems, such as logical or probabilistic inference, and simple manipulations, such as the mere concatenation of trainable learning systems. Therefore, instead of trying to bridge the gap between machine learning systems and sophisticated “all-purpose” inference mechanisms, we can instead algebraically enrich the set of manipulations applicable to training systems, and build reasoning capabilities from the ground up.     

Self-adaptive extreme learning machine

In order to overcome the disadvantage of the traditional algorithm for SLFN (single-hidden layer feedforward neural network), an improved algorithm for SLFN, called extreme learning machine (ELM), is proposed by Huang et al. However, ELM is sensitive to the neuron number in hidden layer and its selection is a difficult-to-solve problem. In this paper, a self-adaptive mechanism is introduced into the ELM. Herein, a new variant of ELM, called self-adaptive extreme learning machine (SaELM), is proposed. SaELM is a self-adaptive learning algorithm that can always select the best neuron number in hidden layer to form the neural networks. There is no need to adjust any parameters in the training process. In order to prove the performance of the SaELM, it is used to solve the Italian wine and iris classification problems. Through the comparisons between SaELM and the traditional back propagation, basic ELM and general regression neural network, the results have proven that SaELM has a faster learning speed and better generalization performance when solving the classification problem.     

极限学习机类不平衡数据学习算法研究

尽管极限学习机因具有快速、简单、易实现及普适的逼近能力等特点被广泛应用于分类、回归及特征学习问题,但是,极限学习机同其他标准分类方法一样将最大化各类总分类性能作为算法的优化目标,因此,在实际应用中遇到数据样本分布不平衡时,算法对大类样本具有性能偏向性。针对极限学习机类不平衡学习问题的研究起步晚,算法少的问题,在介绍了极限学习机类不平衡数据学习研究现状,极限学习机类不平衡数据学习的典型算法-加权极限学习机及其改进算法的基础上,提出一种不需要对原始不平衡样本进行处理的Adaboost提升的加权极限学习机,通过在15个UCI不平衡数据集进行分析实验,实验结果表明提出的算法具有更好的分类性能。     

Evolutionary extreme learning machine

Extreme learning machine (ELM) [G.-B. Huang, Q.-Y. Zhu, C.-K. Siew, Extreme learning machine: a new learning scheme of feedforward neural networks, in: Proceedings of the International Joint Conference on Neural Networks (IJCNN2004), Budapest, Hungary, 25-29 July 2004], a novel learning algorithm much faster than the traditional gradient-based learning algorithms, was proposed recently for single-hidden-layer feedforward neural networks (SLFNs). However, ELM may need higher number of hidden neurons due to the random determination of the input weights and hidden biases. In this paper, a hybrid learning algorithm is proposed which uses the differential evolutionary algorithm to select the input weights and Moore-Penrose (MP) generalized inverse to analytically determine the output weights. Experimental results show that this approach is able to achieve good generalization performance with much more compact networks.     

Symmetric extreme learning machine

Extreme learning machine (ELM) can be considered as a black-box modeling approach that seeks a model representation extracted from the training data. In this paper, a modified ELM algorithm, called symmetric ELM (S-ELM), is proposed by incorporating a priori information of symmetry. S-ELM is realized by transforming the original activation function of hidden neurons into a symmetric one with respect to the input variables of the samples. In theory, S-ELM can approximate N arbitrary distinct samples with zero error. Simulation results show that, in the applications where there exists the prior knowledge of symmetry, S-ELM can obtain better generalization performance, faster learning speed, and more compact network architecture.     

Argument based machine learning

We present a novel approach to machine learning, called ABML (argumentation based ML). This approach combines machine learning from examples with concepts from the field of argumentation. The idea is to provide expert's arguments, or reasons, for some of the learning examples. We require that the theory induced from the examples explains the examples in terms of the given reasons. Thus arguments constrain the combinatorial search among possible hypotheses, and also direct the search towards hypotheses that are more comprehensible in the light of expert's background knowledge. In this paper we realize the idea of ABML as rule learning. We implement ABCN2, an argument-based extension of the CN2 rule learning algorithm, conduct experiments and analyze its performance in comparison with the original CN2 algorithm.     

Quantum speed-up for unsupervised learning

We show how the quantum paradigm can be used to speed up unsupervised learning algorithms. More precisely, we explain how it is possible to accelerate learning algorithms by quantizing some of their subroutines. Quantization refers to the process that partially or totally converts a classical algorithm to its quantum counterpart in order to improve performance. In particular, we give quantized versions of clustering via minimum spanning tree, divisive clustering and k-medians that are faster than their classical analogues. We also describe a distributed version of k-medians that allows the participants to save on the global communication cost of the protocol compared to the classical version. Finally, we design quantum algorithms for the construction of a neighbourhood graph, outlier detection as well as smart initialization of the cluster centres.     

网络结构增长的极端学习机算法

针对极端学习机(extreme learning machine,ELM)结构设计问题,基于隐含层激活函数及其导函数提出一种前向神经网络结构增长算法.首先以Sigmoid函数为例给出了一类基函数的派生特性:导函数可以由其原函数表示.其次,利用这种派生特性提出了ELM结构设计方法,该方法自动生成双隐含层前向神经网络,其第1隐含层的结点随机逐一生成.第2隐含层的输出由第1隐含层新添结点的激活函数及其导函数确定,输出层权值由最小二乘法分析获得.最后给出了所提算法收敛性及稳定性的理论证明.对非线性系统辨识及双螺旋分类问题的仿真结果证明了所提算法的有效性.     

Manifold regularized extreme learning machine

Extreme learning machine (ELM) works for generalized single-hidden-layer feedforward networks (SLFNs), and its essence is that the hidden layer of SLFNs need not be tuned. But ELM only utilizes labeled data to carry out the supervised learning task. In order to exploit unlabeled data in the ELM model, we first extend the manifold regularization (MR) framework and then demonstrate the relation between the extended MR framework and ELM. Finally, a manifold regularized extreme learning machine is derived from the proposed framework, which maintains the properties of ELM and can be applicable to large-scale learning problems. Experimental results show that the proposed semi-supervised extreme learning machine is the most cost-efficient method. It tends to have better scalability and achieve satisfactory generalization performance at a relatively faster learning speed than traditional semi-supervised learning algorithms.     

公平性机器学习研究综述

随着机器学习在社会中的广泛使用,带来的歧视问题引发广泛的社会争议,这逐步引起了产业界和学术界对机器学习算法公平性问题的浓厚兴趣。目前对公平性度量和机器学习公平性机制的研究仍然处于初级阶段。本文对公平性机器学习的研究进行了调研,首先从公平性的定义出发,比较了衡量公平性指标的方法,然后调研了公平性数据集,对公平性问题的产生进行了分析,接下来对现有的公平性机器学习算法进行归类和比较,最后总结了当前公平性机器学习研究中存在的问题,并对关键问题和重大挑战进行了讨论。     

Variational Bayesian extreme learning machine

Extreme learning machine (ELM) randomly generates parameters of hidden nodes and then analytically determines the output weights with fast learning speed. The ill-posed problem of parameter matrix of hidden nodes directly causes unstable performance, and the automatical selection problem of the hidden nodes is critical to holding the high efficiency of ELM. Focusing on the ill-posed problem and the automatical selection problem of the hidden nodes, this paper proposes the variational Bayesian extreme learning machine (VBELM). First, the Bayesian probabilistic model is involved into ELM, where the Bayesian prior distribution can avoid the ill-posed problem of hidden node matrix. Then, the variational approximation inference is employed in the Bayesian model to compute the posterior distribution and the independent variational hyperparameters approximately, which can be used to select the hidden nodes automatically. Theoretical analysis and experimental results elucidate that VBELM has stabler performance with more compact architectures, which presents probabilistic predictions comparison with traditional point predictions, and it also provides the hyperparameter criterion for hidden node selection.     

Convex incremental extreme learning machine

Unlike the conventional neural network theories and implementations, Huang et al. [Universal approximation using incremental constructive feedforward networks with random hidden nodes, IEEE Transactions on Neural Networks 17(4) (2006) 879–892] have recently proposed a new theory to show that single-hidden-layer feedforward networks (SLFNs) with randomly generated additive or radial basis function (RBF) hidden nodes (according to any continuous sampling distribution) can work as universal approximators and the resulting incremental extreme learning machine (I-ELM) outperforms many popular learning algorithms. I-ELM randomly generates the hidden nodes and analytically calculates the output weights of SLFNs, however, I-ELM does not recalculate the output weights of all the existing nodes when a new node is added. This paper shows that while retaining the same simplicity, the convergence rate of I-ELM can be further improved by recalculating the output weights of the existing nodes based on a convex optimization method when a new hidden node is randomly added. Furthermore, we show that given a type of piecewise continuous computational hidden nodes (possibly not neural alike nodes), if SLFNs can work as universal approximators with adjustable hidden node parameters, from a function approximation point of view the hidden node parameters of such “generalized” SLFNs (including sigmoid networks, RBF networks, trigonometric networks, threshold networks, fuzzy inference systems, fully complex neural networks, high-order networks, ridge polynomial networks, wavelet networks, etc.) can actually be randomly generated according to any continuous sampling distribution. In theory, the parameters of these SLFNs can be analytically determined by ELM instead of being tuned.     

Local coupled extreme learning machine

Due to the significant efficiency and simple implementation, extreme learning machine (ELM) algorithms enjoy much attention in regression and classification applications recently. Many efforts have been paid to enhance the performance of ELM from both methodology (ELM training strategies) and structure (incremental or pruned ELMs) perspectives. In this paper, a local coupled extreme learning machine (LC-ELM) algorithm is presented. By assigning an address to each hidden node in the input space, LC-ELM introduces a decoupler framework to ELM in order to reduce the complexity of the weight searching space. The activated degree of a hidden node is measured by the membership degree of the similarity between the associated address and the given input. Experimental results confirm that the proposed approach works effectively and generally outperforms the original ELM in both regression and classification applications.     

A wavelet extreme learning machine

Extreme learning machine (ELM) has been widely used in various fields to overcome the problem of low training speed of the conventional neural network. Kernel extreme learning machine (KELM) introduces the kernel method to ELM model, which is applicable in Stat ML. However, if the number of samples in Stat ML is too small, perhaps the unbalanced samples cannot reflect the statistical characteristics of the input data, so that the learning ability of Stat ML will be influenced. At the same time, the mix kernel functions used in KELM are conventional functions. Therefore, the selection of kernel function can still be optimized. Based on the problems above, we introduce the weighted method to KELM to deal with the unbalanced samples. Wavelet kernel functions have been widely used in support vector machine and obtain a good classification performance. Therefore, to realize a combination of wavelet analysis and KELM, we introduce wavelet kernel functions to KELM model, which has a mix kernel function of wavelet kernel and sigmoid kernel, and introduce the weighted method to KELM model to balance the sample distribution, and then we propose the weighted wavelet–mix kernel extreme learning machine. The experimental results show that this method can effectively improve the classification ability with better generalization. At the same time, the wavelet kernel functions perform very well compared with the conventional kernel functions in KELM model.     

The security of machine learning

Machine learning’s ability to rapidly evolve to changing and complex situations has helped it become a fundamental tool for computer security. That adaptability is also a vulnerability: attackers can exploit machine learning systems. We present a taxonomy identifying and analyzing attacks against machine learning systems. We show how these classes influence the costs for the attacker and defender, and we give a formal structure defining their interaction. We use our framework to survey and analyze the literature of attacks against machine learning systems. We also illustrate our taxonomy by showing how it can guide attacks against SpamBayes, a popular statistical spam filter. Finally, we discuss how our taxonomy suggests new lines of defenses.     

Single machine scheduling with autonomous learning and induced learning

As an important management tool of winning competitive advantage, induced learning effect has been widely studied in empirical research area. But it is hardly considered in scheduling problems. In this paper, autonomous and induced learning are both taken into consideration. The investment of induced learning is interpreted as specialized time intervals to implement training, knowledge sharing and transferring etc. We present algorithms to determine jointly the optimal job sequence and the optimal position of induced learning intervals, with the objective of minimizing makespan.     

Decay-weighted extreme learning machine for balance and optimization learning

The original extreme learning machine (ELM) was designed for the balanced data, and it balanced misclassification cost of every sample to get the solution. Weighted extreme learning machine assumed that the balance can be achieved through the equality of misclassification costs. This paper improves previous weighted ELM with decay-weight matrix setting for balance and optimization learning. The decay-weight matrix is based on the sample number of each class, but the weight sum values of each class are not necessarily equal. When the number of samples is reduced, the weight sum is also reduced. By adjusting the decaying velocity, classifier could achieve more appropriate boundary position. From the experimental results, the decay-weighted ELM obtains the better effects in solving the imbalance classification tasks, particularly in multiclass tasks. This method was successfully applied to build the prediction model in the urban traffic congestion prediction system.