PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1404.4893공식 코드 · Papers with Code

CTBNCToolkit: Continuous Time Bayesian Network Classifier Toolkit

Continuous time Bayesian network classifiers are designed for temporal classification of multivariate streaming data when time duration of events matters and the class does not change over time. This paper introduces the CTBNCToolkit: an open source Java toolkit which provides a stand-alone application for temporal classification and a library for continuous time Bayesian network classifiers. CTBNCToolkit implements the inference algorithm, the parameter learning algorithm, and the structural learning algorithm for continuous time Bayesian network classifiers. The structural learning algorithm is based on scoring functions: the marginal log-likelihood score and the conditional log-likelihood score are provided. CTBNCToolkit provides also an implementation of the expectation maximization algorithm for clustering purpose. The paper introduces continuous time Bayesian network classifiers. How to use the CTBNToolkit from the command line is described in a specific section. Tutorial examples are included to facilitate users to understand how the toolkit must be used. A section dedicate to the Java library is proposed to help further code extensions.

arXiv:1404.4780

Robust Face Recognition via Adaptive Sparse Representation

Sparse Representation (or coding) based Classification (SRC) has gained great success in face recognition in recent years. However, SRC emphasizes the sparsity too much and overlooks the correlation information which has been demonstrated to be critical in real-world face recognition problems. Besides, some work considers the correlation but overlooks the discriminative ability of sparsity. Different from these existing techniques, in this paper, we propose a framework called Adaptive Sparse Representation based Classification (ASRC) in which sparsity and correlation are jointly considered. Specifically, when the samples are of low correlation, ASRC selects the most discriminative samples for representation, like SRC; when the training samples are highly correlated, ASRC selects most of the correlated and discriminative samples for representation, rather than choosing some related samples randomly. In general, the representation model is adaptive to the correlation structure, which benefits from both $\ell_1$-norm and $\ell_2$-norm. Extensive experiments conducted on publicly available data sets verify the effectiveness and robustness of the proposed algorithm by comparing it with state-of-the-art methods.

arXiv:1404.4661

Learning Fine-grained Image Similarity with Deep Ranking

Learning fine-grained image similarity is a challenging task. It needs to capture between-class and within-class image differences. This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images.It has higher learning capability than models based on hand-crafted features. A novel multiscale network structure has been developed to describe the images effectively. An efficient triplet sampling algorithm is proposed to learn the model with distributed asynchronized stochastic gradient. Extensive experiments show that the proposed algorithm outperforms models based on hand-crafted visual features and deep classification models.

arXiv:1404.4644

A New Space for Comparing Graphs

Finding a new mathematical representations for graph, which allows direct comparison between different graph structures, is an open-ended research direction. Having such a representation is the first prerequisite for a variety of machine learning algorithms like classification, clustering, etc., over graph datasets. In this paper, we propose a symmetric positive semidefinite matrix with the $(i,j)$-{th} entry equal to the covariance between normalized vectors $A^ie$ and $A^je$ ($e$ being vector of all ones) as a representation for graph with adjacency matrix $A$. We show that the proposed matrix representation encodes the spectrum of the underlying adjacency matrix and it also contains information about the counts of small sub-structures present in the graph such as triangles and small paths. In addition, we show that this matrix is a \emph{"graph invariant"}. All these properties make the proposed matrix a suitable object for representing graphs. The representation, being a covariance matrix in a fixed dimensional metric space, gives a mathematical embedding for graphs. This naturally leads to a measure of similarity on graph objects. We define similarity between two given graphs as a Bhattacharya similarity measure between their corresponding covariance matrix representations. As shown in our experimental study on the task of social network classification, such a similarity measure outperforms other widely used state-of-the-art methodologies. Our proposed method is also computationally efficient. The computation of both the matrix representation and the similarity value can be performed in operations linear in the number of edges. This makes our method scalable in practice. We believe our theoretical and empirical results provide evidence for studying truncated power iterations, of the adjacency matrix, to characterize social networks.

arXiv:1404.4641

Multilingual Models for Compositional Distributed Semantics

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of semantically equivalent sentences, while maintaining sufficient distance between those of dissimilar sentences. The models do not rely on word alignments or any syntactic information and are successfully applied to a number of diverse languages. We extend our approach to learn semantic representations at the document level, too. We evaluate these models on two cross-lingual document classification tasks, outperforming the prior state of the art. Through qualitative analysis and the study of pivoting effects we demonstrate that our representations are semantically plausible and can capture semantic relationships across languages without parallel data.

arXiv:1312.6034

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the input image. The first one generates an image, which maximises the class score [Erhan et al., 2009], thus visualising the notion of the class, captured by a ConvNet. The second technique computes a class saliency map, specific to a given image and class. We show that such maps can be employed for weakly supervised object segmentation using classification ConvNets. Finally, we establish the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks [Zeiler et al., 2013].

arXiv:1303.2132

Heuristic Ternary Error-Correcting Output Codes Via Weight Optimization and Layered Clustering-Based Approach

One important classifier ensemble for multiclass classification problems is Error-Correcting Output Codes (ECOCs). It bridges multiclass problems and binary-class classifiers by decomposing multiclass problems to a serial binary-class problems. In this paper, we present a heuristic ternary code, named Weight Optimization and Layered Clustering-based ECOC (WOLC-ECOC). It starts with an arbitrary valid ECOC and iterates the following two steps until the training risk converges. The first step, named Layered Clustering based ECOC (LC-ECOC), constructs multiple strong classifiers on the most confusing binary-class problem. The second step adds the new classifiers to ECOC by a novel Optimized Weighted (OW) decoding algorithm, where the optimization problem of the decoding is solved by the cutting plane algorithm. Technically, LC-ECOC makes the heuristic training process not blocked by some difficult binary-class problem. OW decoding guarantees the non-increase of the training risk for ensuring a small code length. Results on 14 UCI datasets and a music genre classification problem demonstrate the effectiveness of WOLC-ECOC.

arXiv:1211.6085

Random Projections for Linear Support Vector Machines

Let X be a data matrix of rank \rho, whose rows represent n points in d-dimensional space. The linear support vector machine constructs a hyperplane separator that maximizes the 1-norm soft margin. We develop a new oblivious dimension reduction technique which is precomputed and can be applied to any input matrix X. We prove that, with high probability, the margin and minimum enclosing ball in the feature space are preserved to within \epsilon-relative error, ensuring comparable generalization as in the original space in the case of classification. For regression, we show that the margin is preserved to \epsilon-relative error with high probability. We present extensive experiments with real and synthetic data to support our theory.

arXiv:1405.1404

A Network Intrusions Detection System based on a Quantum Bio Inspired Algorithm

Network intrusion detection systems (NIDSs) have a role of identifying malicious activities by monitoring the behavior of networks. Due to the currently high volume of networks trafic in addition to the increased number of attacks and their dynamic properties, NIDSs have the challenge of improving their classification performance. Bio-Inspired Optimization Algorithms (BIOs) are used to automatically extract the the discrimination rules of normal or abnormal behavior to improve the classification accuracy and the detection ability of NIDS. A quantum vaccined immune clonal algorithm with the estimation of distribution algorithm (QVICA-with EDA) is proposed in this paper to build a new NIDS. The proposed algorithm is used as classification algorithm of the new NIDS where it is trained and tested using the KDD data set. Also, the new NIDS is compared with another detection system based on particle swarm optimization (PSO). Results shows the ability of the proposed algorithm of achieving high intrusions classification accuracy where the highest obtained accuracy is 94.8 %.

arXiv:1405.0549

Classification of Diabetes Mellitus using Modified Particle Swarm Optimization and Least Squares Support Vector Machine

Diabetes Mellitus is a major health problem all over the world. Many classification algorithms have been applied for its diagnoses and treatment. In this paper, a hybrid algorithm of Modified-Particle Swarm Optimization and Least Squares- Support Vector Machine is proposed for the classification of type II DM patients. LS-SVM algorithm is used for classification by finding optimal hyper-plane which separates various classes. Since LS-SVM is so sensitive to the changes of its parameter values, Modified-PSO algorithm is used as an optimization technique for LS-SVM parameters. This will Guarantee the robustness of the hybrid algorithm by searching for the optimal values for LS-SVM parameters. The pro-posed Algorithm is implemented and evaluated using Pima Indians Diabetes Data set from UCI repository of machine learning databases. It is also compared with different classifier algorithms which were applied on the same database. The experimental results showed the superiority of the proposed algorithm which could achieve an average classification accuracy of 97.833%.

arXiv:1405.0085

Relative Facial Action Unit Detection

This paper presents a subject-independent facial action unit (AU) detection method by introducing the concept of relative AU detection, for scenarios where the neutral face is not provided. We propose a new classification objective function which analyzes the temporal neighborhood of the current frame to decide if the expression recently increased, decreased or showed no change. This approach is a significant change from the conventional absolute method which decides about AU classification using the current frame, without an explicit comparison with its neighboring frames. Our proposed method improves robustness to individual differences such as face scale and shape, age-related wrinkles, and transitions among expressions (e.g., lower intensity of expressions). Our experiments on three publicly available datasets (Extended Cohn-Kanade (CK+), Bosphorus, and DISFA databases) show significant improvement of our approach over conventional absolute techniques. Keywords: facial action coding system (FACS); relative facial action unit detection; temporal information;

arXiv:1404.7362

Concise comparative summaries (CCS) of large text corpora with a human experiment

In this paper we propose a general framework for topic-specific summarization of large text corpora and illustrate how it can be used for the analysis of news databases. Our framework, concise comparative summarization (CCS), is built on sparse classification methods. CCS is a lightweight and flexible tool that offers a compromise between simple word frequency based methods currently in wide use and more heavyweight, model-intensive methods such as latent Dirichlet allocation (LDA). We argue that sparse methods have much to offer for text analysis and hope CCS opens the door for a new branch of research in this important field. For a particular topic of interest (e.g., China or energy), CSS automatically labels documents as being either on- or off-topic (usually via keyword search), and then uses sparse classification methods to predict these labels with the high-dimensional counts of all the other words and phrases in the documents. The resulting small set of phrases found as predictive are then harvested as the summary. To validate our tool, we, using news articles from the New York Times international section, designed and conducted a human survey to compare the different summarizers with human understanding. We demonstrate our approach with two case studies, a media analysis of the framing of "Egypt" in the New York Times throughout the Arab Spring and an informal comparison of the New York Times' and Wall Street Journal's coverage of "energy." Overall, we find that the Lasso with $L^2$ normalization can be effectively and usefully used to summarize large corpora, regardless of document size.

arXiv:1404.6351

Improving weather radar by fusion and classification

In air traffic management (ATM) all necessary operations (tactical planing, sector configuration, required staffing, runway configuration, routing of approaching aircrafts) rely on accurate measurements and predictions of the current weather situation. An essential basis of information is delivered by weather radar images (WXR), which, unfortunately, exhibit a vast amount of disturbances. Thus, the improvement of these datasets is the key factor for more accurate predictions of weather phenomena and weather conditions. Image processing methods based on texture analysis and geometric operators allow to identify regions including artefacts as well as zones of missing information. Correction of these zones is implemented by exploiting multi-spectral satellite data (Meteosat Second Generation). Results prove that the proposed system for artefact detection and data correction significantly improves the quality of WXR data and, thus, enables more reliable weather now- and forecast leading to increased ATM safety.

arXiv:1404.3366

Learning Deep Convolutional Features for MRI Based Alzheimer's Disease Classification

Effective and accurate diagnosis of Alzheimer's disease (AD) or mild cognitive impairment (MCI) can be critical for early treatment and thus has attracted more and more attention nowadays. Since first introduced, machine learning methods have been gaining increasing popularity for AD related research. Among the various identified biomarkers, magnetic resonance imaging (MRI) are widely used for the prediction of AD or MCI. However, before a machine learning algorithm can be applied, image features need to be extracted to represent the MRI images. While good representations can be pivotal to the classification performance, almost all the previous studies typically rely on human labelling to find the regions of interest (ROI) which may be correlated to AD, such as hippocampus, amygdala, precuneus, etc. This procedure requires domain knowledge and is costly and tedious. Instead of relying on extraction of ROI features, it is more promising to remove manual ROI labelling from the pipeline and directly work on the raw MRI images. In other words, we can let the machine learning methods to figure out these informative and discriminative image structures for AD classification. In this work, we propose to learn deep convolutional image features using unsupervised and supervised learning. Deep learning has emerged as a powerful tool in the machine learning community and has been successfully applied to various tasks. We thus propose to exploit deep features of MRI images based on a pre-trained large convolutional neural network (CNN) for AD and MCI classification, which spares the effort of manual ROI annotation process.

arXiv:1312.6974

Piecewise regression mixture for simultaneous functional data clustering and optimal segmentation

This paper introduces a novel mixture model-based approach for simultaneous clustering and optimal segmentation of functional data which are curves presenting regime changes. The proposed model consists in a finite mixture of piecewise polynomial regression models. Each piecewise polynomial regression model is associated with a cluster, and within each cluster, each piecewise polynomial component is associated with a regime (i.e., a segment). We derive two approaches for learning the model parameters. The former is an estimation approach and consists in maximizing the observed-data likelihood via a dedicated expectation-maximization (EM) algorithm. A fuzzy partition of the curves in K clusters is then obtained at convergence by maximizing the posterior cluster probabilities. The latter however is a classification approach and optimizes a specific classification likelihood criterion through a dedicated classification expectation-maximization (CEM) algorithm. The optimal curve segmentation is performed by using dynamic programming. In the classification approach, both the curve clustering and the optimal segmentation are performed simultaneously as the CEM learning proceeds. We show that the classification approach is the probabilistic version that generalizes the deterministic K-means-like algorithm proposed in H\'ebrail et al. (2010). The proposed approach is evaluated using simulated curves and real-world curves. Comparisons with alternatives including regression mixture models and the K-means like algorithm for piecewise regression demonstrate the effectiveness of the proposed approach.

arXiv:1312.2578

Kernel-based Distance Metric Learning in the Output Space

In this paper we present two related, kernel-based Distance Metric Learning (DML) methods. Their respective models non-linearly map data from their original space to an output space, and subsequent distance measurements are performed in the output space via a Mahalanobis metric. The dimensionality of the output space can be directly controlled to facilitate the learning of a low-rank metric. Both methods allow for simultaneous inference of the associated metric and the mapping to the output space, which can be used to visualize the data, when the output space is 2- or 3-dimensional. Experimental results for a collection of classification tasks illustrate the advantages of the proposed methods over other traditional and kernel-based DML approaches.

arXiv:1405.1605

DepecheMood: a Lexicon for Emotion Analysis from Crowd-Annotated News

While many lexica annotated with words polarity are available for sentiment analysis, very few tackle the harder task of emotion analysis and are usually quite limited in coverage. In this paper, we present a novel approach for extracting - in a totally automated way - a high-coverage and high-precision lexicon of roughly 37 thousand terms annotated with emotion scores, called DepecheMood. Our approach exploits in an original way 'crowd-sourced' affective annotation implicitly provided by readers of news articles from rappler.com. By providing new state-of-the-art performances in unsupervised settings for regression and classification tasks, even using a na\"{\i}ve approach, our experiments show the beneficial impact of harvesting social media data for affective lexicon building.

arXiv:1405.0947

Learning Bilingual Word Representations by Marginalizing Alignments

We present a probabilistic model that simultaneously learns alignments and distributed representations for bilingual data. By marginalizing over word alignments the model captures a larger semantic context than prior work relying on hard alignments. The advantage of this approach is demonstrated in a cross-lingual classification task, where we outperform the prior published state of the art.

arXiv:1405.0876

The Multi-engine ASP Solver ME-ASP: Progress Report

MEASP is a multi-engine solver for ground ASP programs. It exploits algorithm selection techniques based on classification to select one among a set of out-of-the-box heterogeneous ASP solvers used as black-box engines. In this paper we report on (i) a new optimized implementation of MEASP; and (ii) an attempt of applying algorithm selection to non-ground programs. An experimental analysis reported in the paper shows that (i) the new implementation of \measp is substantially faster than the previous version; and (ii) the multi-engine recipe can be applied to the evaluation of non-ground programs with some benefits.

arXiv:1401.3531

Highly comparative feature-based time-series classification

A highly comparative, feature-based approach to time series classification is introduced that uses an extensive database of algorithms to extract thousands of interpretable features from time series. These features are derived from across the scientific time-series analysis literature, and include summaries of time series in terms of their correlation structure, distribution, entropy, stationarity, scaling properties, and fits to a range of time-series models. After computing thousands of features for each time series in a training set, those that are most informative of the class structure are selected using greedy forward feature selection with a linear classifier. The resulting feature-based classifiers automatically learn the differences between classes using a reduced number of time-series properties, and circumvent the need to calculate distances between time series. Representing time series in this way results in orders of magnitude of dimensionality reduction, allowing the method to perform well on very large datasets containing long time series or time series of different lengths. For many of the datasets studied, classification performance exceeded that of conventional instance-based classifiers, including one nearest neighbor classifiers using Euclidean distances and dynamic time warping and, most importantly, the features selected provide an understanding of the properties of the dataset, insight that can guide further scientific investigation.