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

This paper describes a PU learning (Positive and Unlabeled learning) based system for potential URL attack detection. Previous machine learning based solutions for this task mainly formalize it as a supervised learning problem. However, in some scenarios, the data obtained always contains only a handful of known attack URLs, along with a large number of unlabeled instances, making the supervised learning paradigms infeasible. In this work, we formalize this setting as a PU learning problem, and solve it by combining two different strategies (two-stage strategy and cost-sensitive strategy). Experimental results show that the developed system can effectively find potential URL attacks. This system can either be deployed as an assistance for existing system or be employed to help cyber-security engineers to effectively discover potential attack mode so that they can improve the existing system with significantly less efforts.

POSTER: A PU Learning based System for Potential Malicious URL Detection

Previous studies on social networks are often focused on networks with only positive relations between individual nodes. As a significant extension, we conduct the spectral analysis on graphs with both positive and negative edges. Specifically, we investigate the impacts of introducing negative edges and examine patterns in the spectral space of the graph's adjacency matrix. Our theoretical results show that communities in a k-balanced signed graph are distinguishable in the spectral space of its signed adjacency matrix even if connections between communities are dense. This is quite different from recent findings on unsigned graphs, where communities tend to mix together in the spectral space when connections between communities increase. We further conduct theoretical studies based on graph perturbation to examine spectral patterns of general unbalanced signed graphs. We illustrate our theoretical findings with various empirical evaluations.

/pdf/spectral-analysis-of-k-balanced-signed-graphs-5fy3be42hw.pdf

Spectral analysis of k-balanced signed graphs

Similarity measure is one of the keys of a high- performance content-based image retrieval (CBIR) system. Given a pair of images, existing similarity measures usually produce a static and constant similarity score. However, an image can usually be perceived with different meanings and therefore, the similarity between the same pair of images may change when the concept being queried changes. This paper proposes a query-sensitive similarity measure, Qsim, which takes the concept being queried into account in measuring image similarities, by exploiting the query image as well as the images labeled by user in the relevance feedback process. Experimental comparisons to state-of-the-art techniques show that Qsim has superior performance.

/pdf/query-sensitive-similarity-measure-for-content-based-image-28q85hj1e1.pdf

Query-Sensitive Similarity Measure for Content-Based Image Retrieval

Crowdsourcing has been an effective and efficient paradigm for providing labels for large-scale unlabeled data. In the past few years, many methods have been developed for inferring labels from the crowd, but few theoretical analyses have been presented to support this popular human-machine interaction process. In this paper, we theoretically study the quality of labels inferred from crowd workers by majority voting and provide an analysis of label quality that shows that the label error rate decreases exponentially with the number of workers selected for each task. We also study the problem of eliminating low-quality workers from the crowd, and provide a conservative condition for eliminating low-quality workers without eliminating any non-low-quality worker with high probability. We also provide an aggressive condition for eliminating all low-quality workers with high probability.

/pdf/crowdsourcing-label-quality-a-theoretical-analysis-4v9nodctqq.pdf

Crowdsourcing label quality: a theoretical analysis

We investigate online convex optimization in changing environments, and choose the adaptive regret as the performance measure. The goal is to achieve a small regret over every interval so that the comparator is allowed to change over time. Different from previous works that only utilize the convexity condition, this paper further exploits smoothness to improve the adaptive regret. To this end, we develop novel adaptive algorithms for convex and smooth functions, and establish problem-dependent regret bounds over any interval. Our regret bounds are comparable to existing results in the worst case, and become much tighter when the comparator has a small loss.

Zhi-Hua Zhou

Papers

POSTER: A PU Learning based System for Potential Malicious URL Detection

Spectral analysis of k-balanced signed graphs

Query-Sensitive Similarity Measure for Content-Based Image Retrieval

Crowdsourcing label quality: a theoretical analysis

Adaptive Regret of Convex and Smooth Functions