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

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

Data Mining Practical Machine Learning Tools and Techniques

Semi-supervised learning is a learning paradigm concerned with the study of how computers and natural systems such as humans learn in the presence of both labeled and unlabeled data. Traditionally, learning has been studied either in the unsupervised paradigm (e.g., clustering, outlier detection) where all the data is unlabeled, or in the supervised paradigm (e.g., classification, regression) where all the data is labeled.The goal of semi-supervised learning is to understand how combining labeled and unlabeled data may change the learning behavior, and design algorithms that take advantage of such a combination. Semi-supervised learning is of great interest in machine learning and data mining because it can use readily available unlabeled data to improve supervised learning tasks when the labeled data is scarce or expensive. Semi-supervised learning also shows potential as a quantitative tool to understand human category learning, where most of the input is self-evidently unlabeled. In this introductory book, we present some popular semi-supervised learning models, including self-training, mixture models, co-training and multiview learning, graph-based methods, and semi-supervised support vector machines. For each model, we discuss its basic mathematical formulation. The success of semi-supervised learning depends critically on some underlying assumptions. We emphasize the assumptions made by each model and give counterexamples when appropriate to demonstrate the limitations of the different models. In addition, we discuss semi-supervised learning for cognitive psychology. Finally, we give a computational learning theoretic perspective on semi-supervised learning, and we conclude the book with a brief discussion of open questions in the field.

Introduction to Semi-Supervised Learning

Similarity network fusion (SNF) is an approach to integrate multiple data types on the basis of similarity between biological samples rather than individual measurements. The authors demonstrate SNF by constructing patient networks to identify disease subtypes with differential survival profiles.

http://mghassem.mit.edu/wp-content/uploads/2015/06/nmeth.2810.pdf

Similarity network fusion for aggregating data types on a genomic scale

Co-training is a semi-supervised learning paradigm which trains two learners respectively from two different views and lets the learners label some unlabeled examples for each other. In this paper, we present a new PAC analysis on co-training style algorithms. We show that the co-training process can succeed even without two views, given that the two learners have large difference, which explains the success of some co-training style algorithms that do not require two views. Moreover, we theoretically explain that why the co-training process could not improve the performance further after a number of rounds, and present a rough estimation on the appropriate round to terminate co-training to avoid some wasteful learning rounds.

/pdf/analyzing-co-training-style-algorithms-nhq4j7fwei.pdf

Analyzing Co-training Style Algorithms

In this paper, we present a new analysis on co-training, a representative paradigm of disagreement-based semi-supervised learning methods. In our analysis the co-training process is viewed as a combinative label propagation over two views; this provides a possibility to bring the graph-based and disagreement-based semi-supervised methods into a unified framework. With the analysis we get some insight that has not been disclosed by previous theoretical studies. In particular, we provide the sufficient and necessary condition for co-training to succeed. We also discuss the relationship to previous theoretical results and give some other interesting implications of our results, such as combination of weight matrices and view split.

/pdf/a-new-analysis-of-co-training-499ee1svw9.pdf

A New Analysis of Co-Training

Metric learning is a fundamental problem in computer vision. Different features and algorithms may tackle a problem from different angles, and thus often provide complementary information. In this paper, we propose a fusion algorithm which outputs enhanced metrics by combining multiple given metrics (similarity measures). Unlike traditional co-training style algorithms where multi-view features or multiple data subsets are used for classification or regression, we focus on fusing multiple given metrics through diffusion process in an unsupervised way. Our algorithm has its particular advantage when the input similarity matrices are the outputs from diverse algorithms. We provide both theoretical and empirical explanations to our method. Significant improvements over the state-of-the-art results have been observed on various benchmark datasets. For example, we have achieved 100% accuracy (no longer the bull's eye measure) on the MPEG-7 shape dataset. Our method has a wide range of applications in machine learning and computer vision.

/pdf/unsupervised-metric-fusion-by-cross-diffusion-4qfjyvqmki.pdf

Unsupervised metric fusion by cross diffusion

Deep neural networks have witnessed great successes in various real applications, but it requires a large number of labeled data for training. In this paper, we propose tri-net, a deep neural network which is able to use massive unlabeled data to help learning with limited labeled data. We consider model initialization, diversity augmentation and pseudo-label editing simultaneously. In our work, we utilize output smearing to initialize modules, use fine-tuning on labeled data to augment diversity and eliminate unstable pseudo-labels to alleviate the influence of suspicious pseudolabeled data. Experiments show that our method achieves the best performance in comparison with state-of-the-art semi-supervised deep learning methods. In particular, it achieves 8:30% error rate on CIFAR- 10 by using only 4000 labeled examples.

/pdf/tri-net-for-semi-supervised-deep-learning-1e5jy8sx1s.pdf

Tri-net for semi-supervised deep learning

Multi-view learning has become a hot topic during the past few years. In this paper, we first characterize the sample complexity of multi-view active learning. Under the α-expansion assumption, we get an exponential improvement in the sample complexity from usual O(1/e) to O(log 1/e), requiring neither strong assumption on data distribution such as the data is distributed uniformly over the unit sphere in Rd nor strong assumption on hypothesis class such as linear separators through the origin. We also give an upper bound of the error rate when the α-expansion assumption does not hold. Then, we analyze the combination of multi-view active learning and semi-supervised learning and get a further improvement in the sample complexity. Finally, we study the empirical behavior of the two paradigms, which verifies that the combination of multi-view active learning and semi-supervised learning is efficient.

/pdf/on-multi-view-active-learning-and-the-combination-with-semi-4htu1br05x.pdf

Wei Wang

Papers

Analyzing Co-training Style Algorithms

A New Analysis of Co-Training

Unsupervised metric fusion by cross diffusion

Tri-net for semi-supervised deep learning

On multi-view active learning and the combination with semi-supervised learning