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

The Web has become the largest information repository over the world. Therefore, effectively and efficiently searching the Web becomes a key challenge. Previous research on Web search mainly attempts to exploit the text in the Web pages and the link information between the pages. This paper shows that the Web search performance can be enhanced if image information is considered. In detail, a new Web search framework is proposed, where image snippets are extracted for the Web pages, which are then provided along with text snippets to the user such that it is much easier and more accurate for the user to identify the Web pages he or she expects and to reformulate the initial query. Experimental evaluations demonstrate the promise of the proposed framework.

Improve web search using image snippets

The expected first hitting time is an important issue in theoretical analyses of evolutionary algorithms since it implies the average computational time complexity. In this paper, by exploiting the relationship between the convergence rate and the expected first hitting time, a new approach to estimating the expected first hitting time is proposed. This approach is then applied to four evolutionary algorithms which involve operators of mutation, mutation with population, mutation with recombination, and time-variant mutation, respectively. The results show that the proposed approach is helpful for analyzing a broad range of evolutionary algorithms.

A new approach to estimating the expected first hitting time of evolutionary algorithms

Machine learning techniques have been recognized as powerful tools for the analysis of gene expression data. However, most learning techniques used in class prediction in gene expression analysis during the past years generate black-box models. Although the prediction accuracy of these models could be very well, they provide little insight into the biological facts. This paper holds the recognition that a more reasonable role for machine learning techniques is to generate hypotheses that can be verified or refined by human experts instead of making decisions for human experts. Based on this recognition, a general approach to generate comprehensible hypotheses from gene expression data is described and applied to human acute leukemias as a test case. The results demonstrate the feasibility of using machine learning techniques to help form hypotheses on the relationship between genes and certain diseases.

/pdf/generation-of-comprehensible-hypotheses-from-gene-expression-2lstzg7ly2.pdf

Generation of comprehensible hypotheses from gene expression data

In this paper, a new variant of Bagging named DepenBag is proposed. This algorithm obtains bootstrap samples at first. Then, it employs a causal discoverer to induce from each sample a dependency model expressed as a Directed Acyclic Graph (DAG). The attributes without connections to the class attribute in all the DAGs are then removed. Finally, a component learner is trained from each of the resulted samples to constitute the ensemble. Empirical study shows that DepenBag is effective in building ensembles of nearest neighbor classifiers.

Dependency bagging

We consider the problem of combining and learning over a set of adversarial bandit algorithms with the goal of adaptively tracking the best one on the fly. The CORRAL algorithm of Agarwal et al. (2017) and its variants (Foster et al., 2020a) achieve this goal with a regret overhead of order $\widetilde{O}(\sqrt{MT})$ where $M$ is the number of base algorithms and $T$ is the time horizon. The polynomial dependence on $M$, however, prevents one from applying these algorithms to many applications where $M$ is poly$(T)$ or even larger. Motivated by this issue, we propose a new recipe to corral a larger band of bandit algorithms whose regret overhead has only \emph{logarithmic} dependence on $M$ as long as some conditions are satisfied. As the main example, we apply our recipe to the problem of adversarial linear bandits over a $d$-dimensional $\ell_p$ unit-ball for $p \in (1,2]$. By corralling a large set of $T$ base algorithms, each starting at a different time step, our final algorithm achieves the first optimal switching regret $\widetilde{O}(\sqrt{d S T})$ when competing against a sequence of comparators with $S$ switches (for some known $S$). We further extend our results to linear bandits over a smooth and strongly convex domain as well as unconstrained linear bandits.

Zhi-Hua Zhou

Papers

Improve web search using image snippets

A new approach to estimating the expected first hitting time of evolutionary algorithms

Generation of comprehensible hypotheses from gene expression data

Dependency bagging

Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits