PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1609.08389

A Hackathon for Classical Tibetan

We describe the course of a hackathon dedicated to the development of linguistic tools for Tibetan Buddhist studies. Over a period of five days, a group of seventeen scholars, scientists, and students developed and compared algorithms for intertextual alignment and text classification, along with some basic language tools, including a stemmer and word segmenter.

arXiv:1609.08364공식 코드 · Papers with Code

Automated Breast Lesion Segmentation in Ultrasound Images

The main objective of this project is to segment different breast ultrasound images to find out lesion area by discarding the low contrast regions as well as the inherent speckle noise. The proposed method consists of three stages (removing noise, segmentation, classification) in order to extract the correct lesion. We used normalized cuts approach to segment ultrasound images into regions of interest where we can possibly finds the lesion, and then K-means classifier is applied to decide finally the location of the lesion. For every original image, an annotated ground-truth image is given to perform comparison with the obtained experimental results, providing accurate evaluation measures.

arXiv:1609.08291

Image Retrieval with Fisher Vectors of Binary Features

Recently, the Fisher vector representation of local features has attracted much attention because of its effectiveness in both image classification and image retrieval. Another trend in the area of image retrieval is the use of binary features such as ORB, FREAK, and BRISK. Considering the significant performance improvement for accuracy in both image classification and retrieval by the Fisher vector of continuous feature descriptors, if the Fisher vector were also to be applied to binary features, we would receive similar benefits in binary feature based image retrieval and classification. In this paper, we derive the closed-form approximation of the Fisher vector of binary features modeled by the Bernoulli mixture model. We also propose accelerating the Fisher vector by using the approximate value of posterior probability. Experiments show that the Fisher vector representation significantly improves the accuracy of image retrieval compared with a bag of binary words approach.

arXiv:1609.08201

Robust Time-Series Retrieval Using Probabilistic Adaptive Segmental Alignment

Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in many application settings matching subsequences (segments) instead of individual samples may bring in additional robustness to noise or local non-causal perturbations. This paper presents an approach to segmental sequence alignment that jointly segments and aligns two sequences, generalizing the traditional per-sample alignment. To accomplish this task, we introduce a distance metric between segments based on average pairwise distances and then present a modified pair-HMM (PHMM) that incorporates the proposed distance metric to solve the joint segmentation and alignment task. We also propose a relaxation to our model that improves the computational efficiency of the generic segmental PHMM. Our results demonstrate that this new measure of sequence similarity can lead to improved classification performance, while being resilient to noise, on a variety of sequence retrieval problems, from EEG to motion sequence classification.

arXiv:1609.07770

Random Forest for Malware Classification

The challenge in engaging malware activities involves the correct identification and classification of different malware variants. Various malwares incorporate code obfuscation methods that alters their code signatures effectively countering antimalware detection techniques utilizing static methods and signature database. In this study, we utilized an approach of converting a malware binary into an image and use Random Forest to classify various malware families. The resulting accuracy of 0.9562 exhibits the effectivess of the method in detecting malware

arXiv:1609.07724

The RNN-ELM Classifier

In this paper we examine learning methods combining the Random Neural Network, a biologically inspired neural network and the Extreme Learning Machine that achieve state of the art classification performance while requiring much shorter training time. The Random Neural Network is a integrate and fire computational model of a neural network whose mathematical structure permits the efficient analysis of large ensembles of neurons. An activation function is derived from the RNN and used in an Extreme Learning Machine. We compare the performance of this combination against the ELM with various activation functions, we reduce the input dimensionality via PCA and compare its performance vs. autoencoder based versions of the RNN-ELM.

arXiv:1609.07082

Large Margin Nearest Neighbor Classification using Curved Mahalanobis Distances

We consider the supervised classification problem of machine learning in Cayley-Klein projective geometries: We show how to learn a curved Mahalanobis metric distance corresponding to either the hyperbolic geometry or the elliptic geometry using the Large Margin Nearest Neighbor (LMNN) framework. We report on our experimental results, and further consider the case of learning a mixed curved Mahalanobis distance. Besides, we show that the Cayley-Klein Voronoi diagrams are affine, and can be built from an equivalent (clipped) power diagrams, and that Cayley-Klein balls have Mahalanobis shapes with displaced centers.

arXiv:1609.06417

Matrix Variate RBM Model with Gaussian Distributions

Restricted Boltzmann Machine (RBM) is a particular type of random neural network models modeling vector data based on the assumption of Bernoulli distribution. For multi-dimensional and non-binary data, it is necessary to vectorize and discretize the information in order to apply the conventional RBM. It is well-known that vectorization would destroy internal structure of data, and the binary units will limit the applying performance due to fickle real data. To address the issue, this paper proposes a Matrix variate Gaussian Restricted Boltzmann Machine (MVGRBM) model for matrix data whose entries follow Gaussian distributions. Compared with some other RBM algorithm, MVGRBM can model real value data better and it has good performance in image classification.

arXiv:1609.09432

A Searchlight Factor Model Approach for Locating Shared Information in Multi-Subject fMRI Analysis

There is a growing interest in joint multi-subject fMRI analysis. The challenge of such analysis comes from inherent anatomical and functional variability across subjects. One approach to resolving this is a shared response factor model. This assumes a shared and time synchronized stimulus across subjects. Such a model can often identify shared information, but it may not be able to pinpoint with high resolution the spatial location of this information. In this work, we examine a searchlight based shared response model to identify shared information in small contiguous regions (searchlights) across the whole brain. Validation using classification tasks demonstrates that we can pinpoint informative local regions.

arXiv:1609.09251

Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification

This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features in the paradigm of kernel methods on infinite-dimensional Riemannian manifolds. Our formulation provides in particular a rich representation of image features by exploiting their non-linear correlations. Theoretically, we provide a finite-dimensional approximation of the Log-Hilbert-Schmidt (Log-HS) distance between covariance operators that is scalable to large datasets, while maintaining an effective discriminating capability. This allows us to efficiently approximate any continuous shift-invariant kernel defined using the Log-HS distance. At the same time, we prove that the Log-HS inner product between covariance operators is only approximable by its finite-dimensional counterpart in a very limited scenario. Consequently, kernels defined using the Log-HS inner product, such as polynomial kernels, are not scalable in the same way as shift-invariant kernels. Computationally, we apply the approximate Log-HS distance formulation to covariance operators of both handcrafted and convolutional features, exploiting both the expressiveness of these features and the power of the covariance representation. Empirically, we tested our framework on the task of image classification on twelve challenging datasets. In almost all cases, the results obtained outperform other state of the art methods, demonstrating the competitiveness and potential of our framework.

arXiv:1609.09199

Structure-Aware Classification using Supervised Dictionary Learning

In this paper, we propose a supervised dictionary learning algorithm that aims to preserve the local geometry in both dimensions of the data. A graph-based regularization explicitly takes into account the local manifold structure of the data points. A second graph regularization gives similar treatment to the feature domain and helps in learning a more robust dictionary. Both graphs can be constructed from the training data or learned and adapted along the dictionary learning process. The combination of these two terms promotes the discriminative power of the learned sparse representations and leads to improved classification accuracy. The proposed method was evaluated on several different datasets, representing both single-label and multi-label classification problems, and demonstrated better performance compared with other dictionary based approaches.

arXiv:1609.09018

Deep Architectures for Face Attributes

We train a deep convolutional neural network to perform identity classification using a new dataset of public figures annotated with age, gender, ethnicity and emotion labels, and then fine-tune it for attribute classification. An optimal sharing pattern of computational resources within this network is determined by experiment, requiring only 1 G flops to produce all predictions. Rather than fine-tune by relearning weights in one additional layer after the penultimate layer of the identity network, we try several different depths for each attribute. We find that prediction of age and emotion is improved by fine-tuning from earlier layers onward, presumably because deeper layers are progressively invariant to non-identity related changes in the input.

arXiv:1609.08965

Graph Based Convolutional Neural Network

The benefit of localized features within the regular domain has given rise to the use of Convolutional Neural Networks (CNNs) in machine learning, with great proficiency in the image classification. The use of CNNs becomes problematic within the irregular spatial domain due to design and convolution of a kernel filter being non-trivial. One solution to this problem is to utilize graph signal processing techniques and the convolution theorem to perform convolutions on the graph of the irregular domain to obtain feature map responses to learnt filters. We propose graph convolution and pooling operators analogous to those in the regular domain. We also provide gradient calculations on the input data and spectral filters, which allow for the deep learning of an irregular spatial domain problem. Signal filters take the form of spectral multipliers, applying convolution in the graph spectral domain. Applying smooth multipliers results in localized convolutions in the spatial domain, with smoother multipliers providing sharper feature maps. Algebraic Multigrid is presented as a graph pooling method, reducing the resolution of the graph through agglomeration of nodes between layers of the network. Evaluation of performance on the MNIST digit classification problem in both the regular and irregular domain is presented, with comparison drawn to standard CNN. The proposed graph CNN provides a deep learning method for the irregular domains present in the machine learning community, obtaining 94.23% on the regular grid, and 94.96% on a spatially irregular subsampled MNIST.

arXiv:1609.08703공식 코드 · Papers with Code

Optimizing Neural Network Hyperparameters with Gaussian Processes for Dialog Act Classification

Systems based on artificial neural networks (ANNs) have achieved state-of-the-art results in many natural language processing tasks. Although ANNs do not require manually engineered features, ANNs have many hyperparameters to be optimized. The choice of hyperparameters significantly impacts models' performances. However, the ANN hyperparameters are typically chosen by manual, grid, or random search, which either requires expert experiences or is computationally expensive. Recent approaches based on Bayesian optimization using Gaussian processes (GPs) is a more systematic way to automatically pinpoint optimal or near-optimal machine learning hyperparameters. Using a previously published ANN model yielding state-of-the-art results for dialog act classification, we demonstrate that optimizing hyperparameters using GP further improves the results, and reduces the computational time by a factor of 4 compared to a random search. Therefore it is a useful technique for tuning ANN models to yield the best performances for natural language processing tasks.

arXiv:1609.08675

YouTube-8M: A Large-Scale Video Classification Benchmark

Many recent advancements in Computer Vision are attributed to large datasets. Open-source software packages for Machine Learning and inexpensive commodity hardware have reduced the barrier of entry for exploring novel approaches at scale. It is possible to train models over millions of examples within a few days. Although large-scale datasets exist for image understanding, such as ImageNet, there are no comparable size video classification datasets. In this paper, we introduce YouTube-8M, the largest multi-label video classification dataset, composed of ~8 million videos (500K hours of video), annotated with a vocabulary of 4800 visual entities. To get the videos and their labels, we used a YouTube video annotation system, which labels videos with their main topics. While the labels are machine-generated, they have high-precision and are derived from a variety of human-based signals including metadata and query click signals. We filtered the video labels (Knowledge Graph entities) using both automated and manual curation strategies, including asking human raters if the labels are visually recognizable. Then, we decoded each video at one-frame-per-second, and used a Deep CNN pre-trained on ImageNet to extract the hidden representation immediately prior to the classification layer. Finally, we compressed the frame features and make both the features and video-level labels available for download. We trained various (modest) classification models on the dataset, evaluated them using popular evaluation metrics, and report them as baselines. Despite the size of the dataset, some of our models train to convergence in less than a day on a single machine using TensorFlow. We plan to release code for training a TensorFlow model and for computing metrics.

arXiv:1609.08550

Correct classification for big/smart/fast data machine learning

Table (database) / Relational database Classification for big/smart/fast data machine learning is one of the most important tasks of predictive analytics and extracting valuable information from data. It is core applied technique for what now understood under data science and/or artificial intelligence. Widely used Decision Tree (Random Forest) and rare used rule based PRISM , VFST, etc classifiers are empirical substitutions of theoretically correct to use Boolean functions minimization. Developing Minimization of Boolean functions algorithms is started long time ago by Edward Veitch's 1952. Since it, big efforts by wide scientific/industrial community was done to find feasible solution of Boolean functions minimization. In this paper we propose consider table data classification from mathematical point of view, as minimization of Boolean functions. It is shown that data representation may be transformed to Boolean functions form and how to use known algorithms. For simplicity, binary output function is used for development, what opens doors for multivalued outputs developments.

arXiv:1609.08349

Multi-label Methods for Prediction with Sequential Data

The number of methods available for classification of multi-label data has increased rapidly over recent years, yet relatively few links have been made with the related task of classification of sequential data. If labels indices are considered as time indices, the problems can often be seen as equivalent. In this paper we detect and elaborate on connections between multi-label methods and Markovian models, and study the suitability of multi-label methods for prediction in sequential data. From this study we draw upon the most suitable techniques from the area and develop two novel competitive approaches which can be applied to either kind of data. We carry out an empirical evaluation investigating performance on real-world sequential-prediction tasks: electricity demand, and route prediction. As well as showing that several popular multi-label algorithms are in fact easily applicable to sequencing tasks, our novel approaches, which benefit from a unified view of these areas, prove very competitive against established methods.

arXiv:1512.01100

Effective LSTMs for Target-Dependent Sentiment Classification

Target-dependent sentiment classification remains a challenge: modeling the semantic relatedness of a target with its context words in a sentence. Different context words have different influences on determining the sentiment polarity of a sentence towards the target. Therefore, it is desirable to integrate the connections between target word and context words when building a learning system. In this paper, we develop two target dependent long short-term memory (LSTM) models, where target information is automatically taken into account. We evaluate our methods on a benchmark dataset from Twitter. Empirical results show that modeling sentence representation with standard LSTM does not perform well. Incorporating target information into LSTM can significantly boost the classification accuracy. The target-dependent LSTM models achieve state-of-the-art performances without using syntactic parser or external sentiment lexicons.

arXiv:1507.04201

Minimum Density Hyperplanes

Associating distinct groups of objects (clusters) with contiguous regions of high probability density (high-density clusters), is central to many statistical and machine learning approaches to the classification of unlabelled data. We propose a novel hyperplane classifier for clustering and semi-supervised classification which is motivated by this objective. The proposed minimum density hyperplane minimises the integral of the empirical probability density function along it, thereby avoiding intersection with high density clusters. We show that the minimum density and the maximum margin hyperplanes are asymptotically equivalent, thus linking this approach to maximum margin clustering and semi-supervised support vector classifiers. We propose a projection pursuit formulation of the associated optimisation problem which allows us to find minimum density hyperplanes efficiently in practice, and evaluate its performance on a range of benchmark datasets. The proposed approach is found to be very competitive with state of the art methods for clustering and semi-supervised classification.

arXiv:1610.00564

End-to-End Radio Traffic Sequence Recognition with Deep Recurrent Neural Networks

We investigate sequence machine learning techniques on raw radio signal time-series data. By applying deep recurrent neural networks we learn to discriminate between several application layer traffic types on top of a constant envelope modulation without using an expert demodulation algorithm. We show that complex protocol sequences can be learned and used for both classification and generation tasks using this approach.