We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data-labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This survey focuses on categorizing and reviewing the current progress on transfer learning for classification, regression, and clustering problems. In this survey, we discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift. We also explore some potential future issues in transfer learning research.

/pdf/a-survey-on-transfer-learning-1hjmu3otql.pdf

A Survey on Transfer Learning

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

K-flats is a model-based linear manifold clustering algorithm which has been successfully applied in many real-world scenarios. Though some previous works have shown that K-flats doesn't always provide good performance, little effort has been devoted to analyze its inherent deficiency. In this paper, we address this challenge by showing that the deteriorative performance of K-flats can be attributed to the usual reconstruction error measure and the infinitely extending representations of linear models. Then we propose Localized K-flats algorithm (LKF), which introduces localized representations of linear models and a new distortion measure, to remove confusion among different clusters. Experiments on both synthetic and real-world data sets demonstrate the efficiency of the proposed algorithm. Moreover, preliminary experiments show that LKF has the potential to group manifolds with nonlinear structure.

Localized K -flats

In this paper, we propose the Harmonic Recurrent Process (HRP) for forecasting non-stationary time series with periodvarying patterns. HRP works by selectively ensembling recurrent period-varying patterns in harmonic analysis. In contrast to classical forecasting approaches that rely on stationary priors and recurrent neural network approaches that are mostly black boxes, our model is able to deal with irregular nonstationary signals, and its working mechanism is reasonably lucid. We also prove that the stochastic process led by HRP under weak dependence condition is predictive PAC learnable. Comprehensive experiments on simulated and practical tasks validate the effectiveness of HRP.

Harmonic Recurrent Process for Time Series Forecasting

Stability has been explored to study the performance of learning algorithms in recent years and it has been shown that stability is sufficient for generalization and is sufficient and necessary for consistency of ERM in the general learning setting. Previous studies showed that AdaBoost has almost-everywhere uniform stability if the base learner has L1 stability. The L1 stability, however, is too restrictive and we show that AdaBoost becomes constant learner if the base learner is not real-valued learner. Considering that AdaBoost is mostly successful as a classification algorithm, stability analysis for AdaBoost when the base learner is not real-valued learner is an important yet unsolved problem. In this paper, we introduce the approximation stability and prove that approximation stability is sufficient for generalization, and sufficient and necessary for learnability of AERM in the general learning setting. We prove that AdaBoost has approximation stability and thus has good generalization, and an exponential bound for AdaBoost is provided.

/pdf/approximation-stability-and-boosting-2y7su3wmq9.pdf

Approximation stability and boosting

AUC (area under ROC curve) is an important evaluation criterion, which has been popularly used in many learning tasks such as class-imbalance learning, cost-sensitive learning, learning to rank, etc. Many learning approaches try to optimize AUC, while owing to the non-convexity and discontinuousness of AUC, almost all approaches work with surrogate loss functions. Thus, the consistency of AUC is crucial; however, it has been almost untouched before. In this paper, we provide a sufficient condition for the asymptotic consistency of learning approaches based on surrogate loss functions. Based on this result, we prove that exponential loss and logistic loss are consistent with AUC, but hinge loss is inconsistent. Then, we derive the $q$-norm hinge loss and general hinge loss that are consistent with AUC. We also derive the consistent bounds for exponential loss and logistic loss, and obtain the consistent bounds for many surrogate loss functions under the non-noise setting. Further, we disclose an equivalence between the exponential surrogate loss of AUC and exponential surrogate loss of accuracy, and one straightforward consequence of such finding is that AdaBoost and RankBoost are equivalent.

On the Consistency of AUC Pairwise Optimization

Recommender system has attracted much attention during the past decade However, collaborative filtering as a usual technique is vulnerable to malicious attacks that generate fake profiles to manipulate the system Prior research has shown that attacks can significantly affect the robustness of the systems Thus, many attack detection algorithms have been developed for better recommendation Most previous approaches focus on organized malicious attacks, where the attack organizer fakes many user profiles using the same strategy to promote or demote an item In this study, we analyze a different attack style: unorganized malicious attacks, where attackers fake a small number of user profiles to attack the same target item without any organizer This attack style occurs in many real applications, which can significantly affect the robustness of a recommender system, yet relevant studies are inadequate We conduct extensive experiments to study the performance of state-of-the-art attack detection approaches in unorganized malicious attack detection and discuss different approaches regarding their performance Experimental results show that existing attack detection approaches cannot detect unorganized malicious attacks efficiently By explaining the inefficiency of these attack detection approaches and the characteristics of unorganized malicious attacks in detail, we provide a possible research direction to develop new detection schemes for unorganized malicious attack detection

Zhi-Hua Zhou

Papers

Localized K -flats

Harmonic Recurrent Process for Time Series Forecasting

Approximation stability and boosting

On the Consistency of AUC Pairwise Optimization

Unorganized malicious attacks detection