PyTorchKR Papers

최신 논문

총 12,307편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1907.04613

Neural Networks as Explicit Word-Based Rules

Filters of convolutional networks used in computer vision are often visualized as image patches that maximize the response of the filter. We use the same approach to interpret weight matrices in simple architectures for natural language processing tasks. We interpret a convolutional network for sentiment classification as word-based rules. Using the rule, we recover the performance of the original model.

arXiv:1907.04563

Deep Multi Label Classification in Affine Subspaces

Multi-label classification (MLC) problems are becoming increasingly popular in the context of medical imaging. This has in part been driven by the fact that acquiring annotations for MLC is far less burdensome than for semantic segmentation and yet provides more expressiveness than multi-class classification. However, to train MLCs, most methods have resorted to similar objective functions as with traditional multi-class classification settings. We show in this work that such approaches are not optimal and instead propose a novel deep MLC classification method in affine subspace. At its core, the method attempts to pull features of class-labels towards different affine subspaces while maximizing the distance between them. We evaluate the method using two MLC medical imaging datasets and show a large performance increase compared to previous multi-label frameworks. This method can be seen as a plug-in replacement loss function and is trainable in an end-to-end fashion.

arXiv:1907.03752공식 코드 · Papers with Code

Improving short text classification through global augmentation methods

We study the effect of different approaches to text augmentation. To do this we use 3 datasets that include social media and formal text in the form of news articles. Our goal is to provide insights for practitioners and researchers on making choices for augmentation for classification use cases. We observe that Word2vec-based augmentation is a viable option when one does not have access to a formal synonym model (like WordNet-based augmentation). The use of \emph{mixup} further improves performance of all text based augmentations and reduces the effects of overfitting on a tested deep learning model. Round-trip translation with a translation service proves to be harder to use due to cost and as such is less accessible for both normal and low resource use-cases.

arXiv:1907.04233

Contextual One-Class Classification in Data Streams

In machine learning, the one-class classification problem occurs when training instances are only available from one class. It has been observed that making use of this class's structure, or its different contexts, may improve one-class classifier performance. Although this observation has been demonstrated for static data, a rigorous application of the idea within the data stream environment is lacking. To address this gap, we propose the use of context to guide one-class classifier learning in data streams, paying particular attention to the challenges presented by the dynamic learning environment. We present three frameworks that learn contexts and conduct experiments with synthetic and benchmark data streams. We conclude that the paradigm of contexts in data streams can be used to improve the performance of streaming one-class classifiers.

arXiv:1907.04223

Characterizing Inter-Layer Functional Mappings of Deep Learning Models

Deep learning architectures have demonstrated state-of-the-art performance for object classification and have become ubiquitous in commercial products. These methods are often applied without understanding (a) the difficulty of a classification task given the input data, and (b) how a specific deep learning architecture transforms that data. To answer (a) and (b), we illustrate the utility of a multivariate nonparametric estimator of class separation, the Henze-Penrose (HP) statistic, in the original as well as layer-induced representations. Given an $N$-class problem, our contribution defines the $C(N,2)$ combinations of HP statistics as a sample from a distribution of class-pair separations. This allows us to characterize the distributional change to class separation induced at each layer of the model. Fisher permutation tests are used to detect statistically significant changes within a model. By comparing the HP statistic distributions between layers, one can statistically characterize: layer adaptation during training, the contribution of each layer to the classification task, and the presence or absence of consistency between training and validation data. This is demonstrated for a simple deep neural network using CIFAR10 with random-labels, CIFAR10, and MNIST datasets.

arXiv:1907.04057

Lidar-based Object Classification with Explicit Occlusion Modeling

LIDAR is one of the most important sensors for Unmanned Ground Vehicles (UGV). Object detection and classification based on lidar point cloud is a key technology for UGV. In object detection and classification, the mutual occlusion between neighboring objects is an important factor affecting the accuracy. In this paper, we consider occlusion as an intrinsic property of the point cloud data. We propose a novel approach that explicitly model the occlusion. The occlusion property is then taken into account in the subsequent classification step. We perform experiments on the KITTI dataset. Experimental results indicate that by utilizing the occlusion property that we modeled, the classifier obtains much better performance.

arXiv:1907.03960

Learning from Thresholds: Fully Automated Classification of Tumor Infiltrating Lymphocytes for Multiple Cancer Types

Deep learning classifiers for characterization of whole slide tissue morphology require large volumes of annotated data to learn variations across different tissue and cancer types. As is well known, manual generation of digital pathology training data is time consuming and expensive. In this paper, we propose a semi-automated method for annotating a group of similar instances at once, instead of collecting only per-instance manual annotations. This allows for a much larger training set, that reflects visual variability across multiple cancer types and thus training of a single network which can be automatically applied to each cancer type without human adjustment. We apply our method to the important task of classifying Tumor Infiltrating Lymphocytes (TILs) in H&E images. Prior approaches were trained for individual cancer types, with smaller training sets and human-in-the-loop threshold adjustment. We utilize these thresholded results as large scale "semi-automatic" annotations. Combined with existing manual annotations, our trained deep networks are able to automatically produce better TIL prediction results in 12 cancer types, compared to the human-in-the-loop approach.

arXiv:1907.03532공식 코드 · Papers with Code

Classification of Macromolecule Type Based on Sequences of Amino Acids Using Deep Learning

The classification of amino acids and their sequence analysis plays a vital role in life sciences and is a challenging task. This article uses and compares state-of-the-art deep learning models like convolution neural networks (CNN), long short-term memory (LSTM), and gated recurrent units (GRU) to solve macromolecule classification problems using amino acids. These models have efficient frameworks for solving a broad spectrum of complex learning problems compared to traditional machine learning techniques. We use word embedding to represent the amino acid sequences as vectors. The CNN extracts features from amino acid sequences, which are treated as vectors, then fed to the models mentioned above to train a robust classifier. Our results show that word2vec as embedding combined with VGG-16 performs better than LSTM and GRU. The proposed approach gets an error rate of 1.5%.

arXiv:1907.03110

ANETAC: Arabic Named Entity Transliteration and Classification Dataset

In this paper, we make freely accessible ANETAC our English-Arabic named entity transliteration and classification dataset that we built from freely available parallel translation corpora. The dataset contains 79,924 instances, each instance is a triplet (e, a, c), where e is the English named entity, a is its Arabic transliteration and c is its class that can be either a Person, a Location, or an Organization. The ANETAC dataset is mainly aimed for the researchers that are working on Arabic named entity transliteration, but it can also be used for named entity classification purposes.

arXiv:1907.03313

Smart Grid Cyber Attacks Detection using Supervised Learning and Heuristic Feature Selection

False Data Injection (FDI) attacks are a common form of Cyber-attack targetting smart grids. Detection of stealthy FDI attacks is impossible by the current bad data detection systems. Machine learning is one of the alternative methods proposed to detect FDI attacks. This paper analyzes three various supervised learning techniques, each to be used with three different feature selection (FS) techniques. These methods are tested on the IEEE 14-bus, 57-bus, and 118-bus systems for evaluation of versatility. Accuracy of the classification is used as the main evaluation method for each detection technique. Simulation study clarify the supervised learning combined with heuristic FS methods result in an improved performance of the classification algorithms for FDI attack detection.

arXiv:1907.03250

Resource-Efficient Wearable Computing for Real-Time Reconfigurable Machine Learning: A Cascading Binary Classification

Advances in embedded systems have enabled integration of many lightweight sensory devices within our daily life. In particular, this trend has given rise to continuous expansion of wearable sensors in a broad range of applications from health and fitness monitoring to social networking and military surveillance. Wearables leverage machine learning techniques to profile behavioral routine of their end-users through activity recognition algorithms. Current research assumes that such machine learning algorithms are trained offline. In reality, however, wearables demand continuous reconfiguration of their computational algorithms due to their highly dynamic operation. Developing a personalized and adaptive machine learning model requires real-time reconfiguration of the model. Due to stringent computation and memory constraints of these embedded sensors, the training/re-training of the computational algorithms need to be memory- and computation-efficient. In this paper, we propose a framework, based on the notion of online learning, for real-time and on-device machine learning training. We propose to transform the activity recognition problem from a multi-class classification problem to a hierarchical model of binary decisions using cascading online binary classifiers. Our results, based on Pegasos online learning, demonstrate that the proposed approach achieves 97% accuracy in detecting activities of varying intensities using a limited memory while power usages of the system is reduced by more than 40%.

arXiv:1907.03247

Resource-Efficient Computing in Wearable Systems

We propose two optimization techniques to minimize memory usage and computation while meeting system timing constraints for real-time classification in wearable systems. Our method derives a hierarchical classifier structure for Support Vector Machine (SVM) in order to reduce the amount of computations, based on the probability distribution of output classes occurrences. Also, we propose a memory optimization technique based on SVM parameters, which results in storing fewer support vectors and as a result requiring less memory. To demonstrate the efficiency of our proposed techniques, we performed an activity recognition experiment and were able to save up to 35% and 56% in memory storage when classifying 14 and 6 different activities, respectively. In addition, we demonstrated that there is a trade-off between accuracy of classification and memory savings, which can be controlled based on application requirements.

arXiv:1907.03220

Skin Lesion Analyser: An Efficient Seven-Way Multi-Class Skin Cancer Classification Using MobileNet

Skin cancer, a major form of cancer, is a critical public health problem with 123,000 newly diagnosed melanoma cases and between 2 and 3 million non-melanoma cases worldwide each year. The leading cause of skin cancer is high exposure of skin cells to UV radiation, which can damage the DNA inside skin cells leading to uncontrolled growth of skin cells. Skin cancer is primarily diagnosed visually employing clinical screening, a biopsy, dermoscopic analysis, and histopathological examination. It has been demonstrated that the dermoscopic analysis in the hands of inexperienced dermatologists may cause a reduction in diagnostic accuracy. Early detection and screening of skin cancer have the potential to reduce mortality and morbidity. Previous studies have shown Deep Learning ability to perform better than human experts in several visual recognition tasks. In this paper, we propose an efficient seven-way automated multi-class skin cancer classification system having performance comparable with expert dermatologists. We used a pretrained MobileNet model to train over HAM10000 dataset using transfer learning. The model classifies skin lesion image with a categorical accuracy of 83.1 percent, top2 accuracy of 91.36 percent and top3 accuracy of 95.34 percent. The weighted average of precision, recall, and f1-score were found to be 0.89, 0.83, and 0.83 respectively. The model has been deployed as a web application for public use at (https://saketchaturvedi.github.io). This fast, expansible method holds the potential for substantial clinical impact, including broadening the scope of primary care practice and augmenting clinical decision-making for dermatology specialists.

arXiv:1907.03164공식 코드 · Papers with Code

Towards Debugging Deep Neural Networks by Generating Speech Utterances

Deep neural networks (DNN) are able to successfully process and classify speech utterances. However, understanding the reason behind a classification by DNN is difficult. One such debugging method used with image classification DNNs is activation maximization, which generates example-images that are classified as one of the classes. In this work, we evaluate applicability of this method to speech utterance classifiers as the means to understanding what DNN "listens to". We trained a classifier using the speech command corpus and then use activation maximization to pull samples from the trained model. Then we synthesize audio from features using WaveNet vocoder for subjective analysis. We measure the quality of generated samples by objective measurements and crowd-sourced human evaluations. Results show that when combined with the prior of natural speech, activation maximization can be used to generate examples of different classes. Based on these results, activation maximization can be used to start opening up the DNN black-box in speech tasks.

arXiv:1907.03149

Intelligent Systems Design for Malware Classification Under Adversarial Conditions

The use of machine learning and intelligent systems has become an established practice in the realm of malware detection and cyber threat prevention. In an environment characterized by widespread accessibility and big data, the feasibility of malware classification without the use of artificial intelligence-based techniques has been diminished exponentially. Also characteristic of the contemporary realm of automated, intelligent malware detection is the threat of adversarial machine learning. Adversaries are looking to target the underlying data and/or algorithm responsible for the functionality of malware classification to map its behavior or corrupt its functionality. The ends of such adversaries are bypassing the cyber security measures and increasing malware effectiveness. The focus of this research is the design of an intelligent systems approach using machine learning that can accurately and robustly classify malware under adversarial conditions. Such an outcome ultimately relies on increased flexibility and adaptability to build a model robust enough to identify attacks on the underlying algorithm.

arXiv:1907.03123

Revisiting Metric Learning for Few-Shot Image Classification

The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison between query and support examples. However, the importance of feature embedding, i.e., exploring the relationship among training samples, is neglected. In this work, we present a simple yet powerful baseline for few-shot classification by emphasizing the importance of feature embedding. Specifically, we revisit the classical triplet network from deep metric learning, and extend it into a deep K-tuplet network for few-shot learning, utilizing the relationship among the input samples to learn a general representation learning via episode-training. Once trained, our network is able to extract discriminative features for unseen novel categories and can be seamlessly incorporated with a non-linear distance metric function to facilitate the few-shot classification. Our result on the miniImageNet benchmark outperforms other metric-based few-shot classification methods. More importantly, when evaluated on completely different datasets (Caltech-101, CUB-200, Stanford Dogs and Cars) using the model trained with miniImageNet, our method significantly outperforms prior methods, demonstrating its superior capability to generalize to unseen classes.

arXiv:1907.03010

Financial Time Series Data Processing for Machine Learning

This article studies the financial time series data processing for machine learning. It introduces the most frequent scaling methods, then compares the resulting stationarity and preservation of useful information for trend forecasting. It proposes an empirical test based on the capability to learn simple data relationship with simple models. It also speaks about the data split method specific to time series, avoiding unwanted overfitting and proposes various labelling for classification and regression.

논문 ID: publication/3272631

Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers

A method for the automatic classification of electrocardiograms (ECG) based on the combination of multiple Support Vector Machines (SVMs) is presented in this work. The method relies on the time intervals between consequent beats and their morphology for the ECG characterisation. Different descriptors based on wavelets, local binary patterns (LBP), higher order statistics (HOS) and several amplitude values were employed. Instead of concatenating all these features to feed a single SVM model, we propose to train specific SVM models for each type of feature. In order to obtain the final prediction, the decisions of the different models are combined with the product, sum, and majority rules. The designed methodology approaches are tested on the public MIT-BIH arrhythmia database, classifying four kinds of abnormal and normal beats. Our approach based on an ensemble of SVMs offered a satisfactory performance, improving the results when compared to a single SVM model using the same features. Additionally, our approach also showed better results in comparison with previous machine learning approaches of the state-of-the-art.

arXiv:1907.03715

Predicting Customer Call Intent by Analyzing Phone Call Transcripts based on CNN for Multi-Class Classification

Auto dealerships receive thousands of calls daily from customers who are interested in sales, service, vendors and jobseekers. With so many calls, it is very important for auto dealers to understand the intent of these calls to provide positive customer experiences that ensure customer satisfaction, deep customer engagement to boost sales and revenue, and optimum allocation of agents or customer service representatives across the business. In this paper, we define the problem of customer phone call intent as a multi-class classification problem stemming from the large database of recorded phone call transcripts. To solve this problem, we develop a convolutional neural network (CNN)-based supervised learning model to classify the customer calls into four intent categories: sales, service, vendor and jobseeker. Experimental results show that with the thrust of our scalable data labeling method to provide sufficient training data, the CNN-based predictive model performs very well on long text classification according to the quantitative metrics of F1-Score, precision, recall, and accuracy.

arXiv:1907.03373공식 코드 · Papers with Code

Privacy-Preserving Classification with Secret Vector Machines

Today, large amounts of valuable data are distributed among millions of user-held devices, such as personal computers, phones, or Internet-of-things devices. Many companies collect such data with the goal of using it for training machine learning models allowing them to improve their services. User-held data is, however, often sensitive, and collecting it is problematic in terms of privacy. We address this issue by proposing a novel way of training a supervised classifier in a distributed setting akin to the recently proposed federated learning paradigm, but under the stricter privacy requirement that the server that trains the model is assumed to be untrusted and potentially malicious. We thus preserve user privacy by design, rather than by trust. In particular, our framework, called secret vector machine (SecVM), provides an algorithm for training linear support vector machines (SVM) in a setting in which data-holding clients communicate with an untrusted server by exchanging messages designed to not reveal any personally identifiable information. We evaluate our model in two ways. First, in an offline evaluation, we train SecVM to predict user gender from tweets, showing that we can preserve user privacy without sacrificing classification performance. Second, we implement SecVM's distributed framework for the Cliqz web browser and deploy it for predicting user gender in a large-scale online evaluation with thousands of clients, outperforming baselines by a large margin and thus showcasing that SecVM is suitable for production environments.