PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1310.3003

Distance-weighted Support Vector Machine

A novel linear classification method that possesses the merits of both the Support Vector Machine (SVM) and the Distance-weighted Discrimination (DWD) is proposed in this article. The proposed Distance-weighted Support Vector Machine method can be viewed as a hybrid of SVM and DWD that finds the classification direction by minimizing mainly the DWD loss, and determines the intercept term in the SVM manner. We show that our method inheres the merit of DWD, and hence, overcomes the data-piling and overfitting issue of SVM. On the other hand, the new method is not subject to imbalanced data issue which was a main advantage of SVM over DWD. It uses an unusual loss which combines the Hinge loss (of SVM) and the DWD loss through a trick of axillary hyperplane. Several theoretical properties, including Fisher consistency and asymptotic normality of the DWSVM solution are developed. We use some simulated examples to show that the new method can compete DWD and SVM on both classification performance and interpretability. A real data application further establishes the usefulness of our approach.

arXiv:1510.04212

Inheritance in Object-Oriented Knowledge Representation

This paper contains the consideration of inheritance mechanism in such knowledge representation models as object-oriented programming, frames and object-oriented dynamic networks. In addition, inheritance within representation of vague and imprecise knowledge are also discussed. New types of inheritance, general classification of all known inheritance types and approach, which allows avoiding in many cases problems with exceptions, redundancy and ambiguity within object-oriented dynamic networks and their fuzzy extension, are introduced in the paper. The proposed approach bases on conception of homogeneous and inhomogeneous or heterogeneous class of objects, which allow building of inheritance hierarchy more flexibly and efficiently.

arXiv:1510.04183

Mathematical Foundations for Designing and Development of Intelligent Systems of Information Analysis

This article is an attempt to combine different ways of working with sets of objects and their classes for designing and development of artificial intelligent systems (AIS) of analysis information, using object-oriented programming (OOP). This paper contains analysis of basic concepts of OOP and their relation with set theory and artificial intelligence (AI). Process of sets and multisets creation from different sides, in particular mathematical set theory, OOP and AI is considered. Definition of object and its properties, homogeneous and inhomogeneous classes of objects, set of objects, multiset of objects and constructive methods of their creation and classification are proposed. In addition, necessity of some extension of existing OOP tools for the purpose of practical implementation AIS of analysis information, using proposed approach, is shown.

arXiv:1510.03507

The intrinsic value of HFO features as a biomarker of epileptic activity

High frequency oscillations (HFOs) are a promising biomarker of epileptic brain tissue and activity. HFOs additionally serve as a prototypical example of challenges in the analysis of discrete events in high-temporal resolution, intracranial EEG data. Two primary challenges are 1) dimensionality reduction, and 2) assessing feasibility of classification. Dimensionality reduction assumes that the data lie on a manifold with dimension less than that of the feature space. However, previous HFO analyses have assumed a linear manifold, global across time, space (i.e. recording electrode/channel), and individual patients. Instead, we assess both a) whether linear methods are appropriate and b) the consistency of the manifold across time, space, and patients. We also estimate bounds on the Bayes classification error to quantify the distinction between two classes of HFOs (those occurring during seizures and those occurring due to other processes). This analysis provides the foundation for future clinical use of HFO features and buides the analysis for other discrete events, such as individual action potentials or multi-unit activity.

arXiv:1510.03199

Interactive multiclass segmentation using superpixel classification

This paper adresses the problem of interactive multiclass segmentation. We propose a fast and efficient new interactive segmentation method called Superpixel Classification-based Interactive Segmentation (SCIS). From a few strokes drawn by a human user over an image, this method extracts relevant semantic objects. To get a fast calculation and an accurate segmentation, SCIS uses superpixel over-segmentation and support vector machine classification. In this paper, we demonstrate that SCIS significantly outperfoms competing algorithms by evaluating its performances on the reference benchmarks of McGuinness and Santner.

arXiv:1510.02983

OmniGraph: Rich Representation and Graph Kernel Learning

OmniGraph, a novel representation to support a range of NLP classification tasks, integrates lexical items, syntactic dependencies and frame semantic parses into graphs. Feature engineering is folded into the learning through convolution graph kernel learning to explore different extents of the graph. A high-dimensional space of features includes individual nodes as well as complex subgraphs. In experiments on a text-forecasting problem that predicts stock price change from news for company mentions, OmniGraph beats several benchmarks based on bag-of-words, syntactic dependencies, and semantic trees. The highly expressive features OmniGraph discovers provide insights into the semantics across distinct market sectors. To demonstrate the method's generality, we also report its high performance results on a fine-grained sentiment corpus.

arXiv:1510.02942

Evaluation of Joint Multi-Instance Multi-Label Learning For Breast Cancer Diagnosis

Multi-instance multi-label (MIML) learning is a challenging problem in many aspects. Such learning approaches might be useful for many medical diagnosis applications including breast cancer detection and classification. In this study subset of digiPATH dataset (whole slide digital breast cancer histopathology images) are used for training and evaluation of six state-of-the-art MIML methods. At the end, performance comparison of these approaches are given by means of effective evaluation metrics. It is shown that MIML-kNN achieve the best performance that is %65.3 average precision, where most of other methods attain acceptable results as well.

arXiv:1509.05177

Some Theorems for Feed Forward Neural Networks

In this paper we introduce a new method which employs the concept of "Orientation Vectors" to train a feed forward neural network and suitable for problems where large dimensions are involved and the clusters are characteristically sparse. The new method is not NP hard as the problem size increases. We `derive' the method by starting from Kolmogrov's method and then relax some of the stringent conditions. We show for most classification problems three layers are sufficient and the network size depends on the number of clusters. We prove as the number of clusters increase from N to N+dN the number of processing elements in the first layer only increases by d(logN), and are proportional to the number of classes, and the method is not NP hard. Many examples are solved to demonstrate that the method of Orientation Vectors requires much less computational effort than Radial Basis Function methods and other techniques wherein distance computations are required, in fact the present method increases logarithmically with problem size compared to the Radial Basis Function method and the other methods which depend on distance computations e.g statistical methods where probabilistic distances are calculated. A practical method of applying the concept of Occum's razor to choose between two architectures which solve the same classification problem has been described. The ramifications of the above findings on the field of Deep Learning have also been briefly investigated and we have found that it directly leads to the existence of certain types of NN architectures which can be used as a "mapping engine", which has the property of "invertibility", thus improving the prospect of their deployment for solving problems involving Deep Learning and hierarchical classification. The latter possibility has a lot of future scope in the areas of machine learning and cloud computing.

arXiv:1510.06093

Content adaptive screen image scaling

This paper proposes an efficient content adaptive screen image scaling scheme for the real-time screen applications like remote desktop and screen sharing. In the proposed screen scaling scheme, a screen content classification step is first introduced to classify the screen image into text and pictorial regions. Afterward, we propose an adaptive shift linear interpolation algorithm to predict the new pixel values with the shift offset adapted to the content type of each pixel. The shift offset for each screen content type is offline optimized by minimizing the theoretical interpolation error based on the training samples respectively. The proposed content adaptive screen image scaling scheme can achieve good visual quality and also keep the low complexity for real-time applications.

arXiv:1510.06024

Robust Semi-Supervised Classification for Multi-Relational Graphs

Graph-regularized semi-supervised learning has been used effectively for classification when (i) instances are connected through a graph, and (ii) labeled data is scarce. If available, using multiple relations (or graphs) between the instances can improve the prediction performance. On the other hand, when these relations have varying levels of veracity and exhibit varying relevance for the task, very noisy and/or irrelevant relations may deteriorate the performance. As a result, an effective weighing scheme needs to be put in place. In this work, we propose a robust and scalable approach for multi-relational graph-regularized semi-supervised classification. Under a convex optimization scheme, we simultaneously infer weights for the multiple graphs as well as a solution. We provide a careful analysis of the inferred weights, based on which we devise an algorithm that filters out irrelevant and noisy graphs and produces weights proportional to the informativeness of the remaining graphs. Moreover, the proposed method is linearly scalable w.r.t. the number of edges in the union of the multiple graphs. Through extensive experiments we show that our method yields superior results under different noise models, and under increasing number of noisy graphs and intensity of noise, as compared to a list of baselines and state-of-the-art approaches.

arXiv:1510.05879

What's the point? Frame-wise Pointing Gesture Recognition with Latent-Dynamic Conditional Random Fields

We use Latent-Dynamic Conditional Random Fields to perform skeleton-based pointing gesture classification at each time instance of a video sequence, where we achieve a frame-wise pointing accuracy of roughly 83%. Subsequently, we determine continuous time sequences of arbitrary length that form individual pointing gestures and this way reliably detect pointing gestures at a false positive detection rate of 0.63%.

arXiv:1510.05477

Accelerometer based Activity Classification with Variational Inference on Sticky HDP-SLDS

As part of daily monitoring of human activities, wearable sensors and devices are becoming increasingly popular sources of data. With the advent of smartphones equipped with acceloremeter, gyroscope and camera; it is now possible to develop activity classification platforms everyone can use conveniently. In this paper, we propose a fast inference method for an unsupervised non-parametric time series model namely variational inference for sticky HDP-SLDS(Hierarchical Dirichlet Process Switching Linear Dynamical System). We show that the proposed algorithm can differentiate various indoor activities such as sitting, walking, turning, going up/down the stairs and taking the elevator using only the acceloremeter of an Android smartphone Samsung Galaxy S4. We used the front camera of the smartphone to annotate activity types precisely. We compared the proposed method with Hidden Markov Models with Gaussian emission probabilities on a dataset of 10 subjects. We showed that the efficacy of the stickiness property. We further compared the variational inference to the Gibbs sampler on the same model and show that variational inference is faster in one order of magnitude.

arXiv:1510.04972

Normalization of Relative and Incomplete Temporal Expressions in Clinical Narratives

We analyze the RI-TIMEXes in temporally annotated corpora and propose two hypotheses regarding the normalization of RI-TIMEXes in the clinical narrative domain: the anchor point hypothesis and the anchor relation hypothesis. We annotate the RI-TIMEXes in three corpora to study the characteristics of RI-TMEXes in different domains. This informed the design of our RI-TIMEX normalization system for the clinical domain, which consists of an anchor point classifier, an anchor relation classifier and a rule-based RI-TIMEX text span parser. We experiment with different feature sets and perform error analysis for each system component. The annotation confirmed the hypotheses that we can simplify the RI-TIMEXes normalization task using two multi-label classifiers. Our system achieves anchor point classification, anchor relation classification and rule-based parsing accuracy of 74.68%, 87.71% and 57.2% (82.09% under relaxed matching criteria) respectively on the held-out test set of the 2012 i2b2 temporal relation challenge. Experiments with feature sets reveals some interesting findings such as the verbal tense feature does not inform the anchor relation classification in clinical narratives as much as the tokens near the RI-TIMEX. Error analysis shows that underrepresented anchor point and anchor relation classes are difficult to detect. We formulate the RI-TIMEX normalization problem as a pair of multi-label classification problems. Considering only the RI-TIMEX extraction and normalization, the system achieves statistically significant improvement over the RI-TIMEX results of the best systems in the 2012 i2b2 challenge.

arXiv:1508.05367

Hidden Markov Models for Gene Sequence Classification: Classifying the VSG genes in the Trypanosoma brucei Genome

The article presents an application of Hidden Markov Models (HMMs) for pattern recognition on genome sequences. We apply HMM for identifying genes encoding the Variant Surface Glycoprotein (VSG) in the genomes of Trypanosoma brucei (T. brucei) and other African trypanosomes. These are parasitic protozoa causative agents of sleeping sickness and several diseases in domestic and wild animals. These parasites have a peculiar strategy to evade the host's immune system that consists in periodically changing their predominant cellular surface protein (VSG). The motivation for using patterns recognition methods to identify these genes, instead of traditional homology based ones, is that the levels of sequence identity (amino acid and DNA sequence) amongst these genes is often below of what is considered reliable in these methods. Among pattern recognition approaches, HMM are particularly suitable to tackle this problem because they can handle more naturally the determination of gene edges. We evaluate the performance of the model using different number of states in the Markov model, as well as several performance metrics. The model is applied using public genomic data. Our empirical results show that the VSG genes on T. brucei can be safely identified (high sensitivity and low rate of false positives) using HMM.

arXiv:1506.02784

Estimating Posterior Ratio for Classification: Transfer Learning from Probabilistic Perspective

Transfer learning assumes classifiers of similar tasks share certain parameter structures. Unfortunately, modern classifiers uses sophisticated feature representations with huge parameter spaces which lead to costly transfer. Under the impression that changes from one classifier to another should be ``simple'', an efficient transfer learning criteria that only learns the ``differences'' is proposed in this paper. We train a \emph{posterior ratio} which turns out to minimizes the upper-bound of the target learning risk. The model of posterior ratio does not have to share the same parameter space with the source classifier at all so it can be easily modelled and efficiently trained. The resulting classifier therefore is obtained by simply multiplying the existing probabilistic-classifier with the learned posterior ratio.

arXiv:1510.08829

Spiking Deep Networks with LIF Neurons

We train spiking deep networks using leaky integrate-and-fire (LIF) neurons, and achieve state-of-the-art results for spiking networks on the CIFAR-10 and MNIST datasets. This demonstrates that biologically-plausible spiking LIF neurons can be integrated into deep networks can perform as well as other spiking models (e.g. integrate-and-fire). We achieved this result by softening the LIF response function, such that its derivative remains bounded, and by training the network with noise to provide robustness against the variability introduced by spikes. Our method is general and could be applied to other neuron types, including those used on modern neuromorphic hardware. Our work brings more biological realism into modern image classification models, with the hope that these models can inform how the brain performs this difficult task. It also provides new methods for training deep networks to run on neuromorphic hardware, with the aim of fast, power-efficient image classification for robotics applications.

arXiv:1510.08633

Nonconvex Penalization in Sparse Estimation: An Approach Based on the Bernstein Function

In this paper we study nonconvex penalization using Bernstein functions whose first-order derivatives are completely monotone. The Bernstein function can induce a class of nonconvex penalty functions for high-dimensional sparse estimation problems. We derive a thresholding function based on the Bernstein penalty and discuss some important mathematical properties in sparsity modeling. We show that a coordinate descent algorithm is especially appropriate for regression problems penalized by the Bernstein function. We also consider the application of the Bernstein penalty in classification problems and devise a proximal alternating linearized minimization method. Based on theory of the Kurdyka-Lojasiewicz inequality, we conduct convergence analysis of these alternating iteration procedures. We particularly exemplify a family of Bernstein nonconvex penalties based on a generalized Gamma measure and conduct empirical analysis for this family.

arXiv:1510.07234

Seam Puckering Objective Evaluation Method for Sewing Process

The paper presents an automated method for the assessment and classification of puckering defects detected during the preproduction control stage of the sewing machine or product inspection. In this respect, we have presented the possible causes and remedies of the wrinkle nonconformities. Subjective factors related to the control environment and operators during the seams evaluation can be reduced using an automated system whose operation is based on image processing. Our implementation involves spectral image analysis using Fourier transform and an unsupervised neural network, the Kohonen Map, employed to classify material specimens, the input images, into five discrete degrees of quality, from grade 5 (best) to grade 1 (the worst).

arXiv:1510.07136

Image Parsing with a Wide Range of Classes and Scene-Level Context

This paper presents a nonparametric scene parsing approach that improves the overall accuracy, as well as the coverage of foreground classes in scene images. We first improve the label likelihood estimates at superpixels by merging likelihood scores from different probabilistic classifiers. This boosts the classification performance and enriches the representation of less-represented classes. Our second contribution consists of incorporating semantic context in the parsing process through global label costs. Our method does not rely on image retrieval sets but rather assigns a global likelihood estimate to each label, which is plugged into the overall energy function. We evaluate our system on two large-scale datasets, SIFTflow and LMSun. We achieve state-of-the-art performance on the SIFTflow dataset and near-record results on LMSun.

arXiv:1510.06492

Generalized Shortest Path Kernel on Graphs

We consider the problem of classifying graphs using graph kernels. We define a new graph kernel, called the generalized shortest path kernel, based on the number and length of shortest paths between nodes. For our example classification problem, we consider the task of classifying random graphs from two well-known families, by the number of clusters they contain. We verify empirically that the generalized shortest path kernel outperforms the original shortest path kernel on a number of datasets. We give a theoretical analysis for explaining our experimental results. In particular, we estimate distributions of the expected feature vectors for the shortest path kernel and the generalized shortest path kernel, and we show some evidence explaining why our graph kernel outperforms the shortest path kernel for our graph classification problem.