PyTorchKR Papers

최신 논문

총 1,314편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1505.03176

Firing Rate Dynamics in Recurrent Spiking Neural Networks with Intrinsic and Network Heterogeneity

Heterogeneity of neural attributes has recently gained a lot of attention and is increasing recognized as a crucial feature in neural processing. Despite its importance, this physiological feature has traditionally been neglected in theoretical studies of cortical neural networks. Thus, there is still a lot unknown about the consequences of cellular and circuit heterogeneity in spiking neural networks. In particular, combining network or synaptic heterogeneity and intrinsic heterogeneity has yet to be considered systematically despite the fact that both are known to exist and likely have significant roles in neural network dynamics. In a canonical recurrent spiking neural network model, we study how these two forms of heterogeneity lead to different distributions of excitatory firing rates. To analytically characterize how these types of heterogeneities affect the network, we employ a dimension reduction method that relies on a combination of Monte Carlo simulations and probability density function equations. We find that the relationship between intrinsic and network heterogeneity has a strong effect on the overall level of heterogeneity of the firing rates. Specifically, this relationship can lead to amplification or attenuation of firing rate heterogeneity, and these effects depend on whether the recurrent network is firing asynchronously or rhythmically firing. These observations are captured with the aforementioned reduction method, and furthermore simpler analytic descriptions based on this dimension reduction method are developed. The final analytic descriptions provide compact and descriptive formulas for how the relationship between intrinsic and network heterogeneity determines the firing rate heterogeneity dynamics in various settings.

arXiv:1502.02764

The Modeling and Quantification of Rhythmic to Non-rhythmic Phenomenon in Electrocardiography during Anesthesia

Variations of instantaneous heart rate appears regularly oscillatory in deeper levels of anesthesia and less regular in lighter levels of anesthesia. It is impossible to observe this "rhythmic-to-non-rhythmic" phenomenon from raw electrocardiography waveform in current standard anesthesia monitors. To explore the possible clinical value, I proposed the adaptive harmonic model, which fits the descriptive property in physiology, and provides adequate mathematical conditions for the quantification. Based on the adaptive harmonic model, multitaper Synchrosqueezing transform was used to provide time-varying power spectrum, which facilitates to compute the quantitative index: "Non-rhythmic-to-Rhythmic Ratio" index (NRR index). I then used a clinical database to analyze the behavior of NRR index and compare it with other standard indices of anesthetic depth. The positive statistical results suggest that NRR index provides addition clinical information regarding motor reaction, which aligns with current standard tools. Furthermore, the ability to indicates the noxious stimulation is an additional finding. Lastly, I have proposed an real-time interpolation scheme to contribute my study further as a clinical application.

arXiv:1501.05836

Consolidating a Link Centered Neural Connectivity Framework with Directed Transfer Function Asymptotics

We present a unified mathematical derivation of the asymptotic behaviour of three of the main forms of \textit{directed transfer function} (DTF) complementing recent partial directed coherence (PDC) results \cite{Baccala2013}. Based on these results and numerical examples we argue for a new directed `link' centered neural connectivity framework to replace the widespread correlation based effective/functional network concepts so that directed network influences between structures become classified as to whether links are \textit{active} in a \textit{direct} or in an \textit{indirect} way thereby leading to the new notions of \textit{Granger connectivity} and \textit{Granger influenciability} which are more descriptive than speaking of Granger causality alone.

arXiv:1309.0408

Descriptive Statistics of the Genome: Phylogenetic Classification of Viruses

The typical process for classifying and submitting a newly sequenced virus to the NCBI database involves two steps. First, a BLAST search is performed to determine likely family candidates. That is followed by checking the candidate families with the Pairwise Sequence Alignment tool for similar species. The submitter's judgement is then used to determine the most likely species classification. The aim of this paper is to show that this process can be automated into a fast, accurate, one-step process using the proposed alignment-free method and properly implemented machine learning techniques. We present a new family of alignment-free vectorizations of the genome, the generalized vector, that maintains the speed of existing alignment-free methods while outperforming all available methods. This new alignment-free vectorization uses the frequency of genomic words (k-mers), as is done in the composition vector, and incorporates descriptive statistics of those k-mers' positional information, as inspired by the natural vector. We analyze 5 different characterizations of genome similarity using $k$-nearest neighbor classification, and evaluate these on two collections of viruses totaling over 10,000 viruses. We show that our proposed method performs better than, or as well as, other methods at every level of the phylogenetic hierarchy. The data and R code is available upon request.

arXiv:2011.14871

ViDi: Descriptive Visual Data Clustering as Radiologist Assistant in COVID-19 Streamline Diagnostic

In the light of the COVID-19 pandemic, deep learning methods have been widely investigated in detecting COVID-19 from chest X-rays. However, a more pragmatic approach to applying AI methods to a medical diagnosis is designing a framework that facilitates human-machine interaction and expert decision making. Studies have shown that categorization can play an essential rule in accelerating real-world decision making. Inspired by descriptive document clustering, we propose a domain-independent explanatory clustering framework to group contextually related instances and support radiologists' decision making. While most descriptive clustering approaches employ domain-specific characteristics to form meaningful clusters, we focus on model-level explanation as a more general-purpose element of every learning process to achieve cluster homogeneity. We employ DeepSHAP to generate homogeneous clusters in terms of disease severity and describe the clusters using favorable and unfavorable saliency maps, which visualize the class discriminating regions of an image. These human-interpretable maps complement radiologist knowledge to investigate the whole cluster at once. Besides, as part of this study, we evaluate a model based on VGG-19, which can identify COVID and pneumonia cases with a positive predictive value of 95% and 97%, respectively, comparable to the recent explainable approaches for COVID diagnosis.

arXiv:2011.13647

Relation Clustering in Narrative Knowledge Graphs

When coping with literary texts such as novels or short stories, the extraction of structured information in the form of a knowledge graph might be hindered by the huge number of possible relations between the entities corresponding to the characters in the novel and the consequent hurdles in gathering supervised information about them. Such issue is addressed here as an unsupervised task empowered by transformers: relational sentences in the original text are embedded (with SBERT) and clustered in order to merge together semantically similar relations. All the sentences in the same cluster are finally summarized (with BART) and a descriptive label extracted from the summary. Preliminary tests show that such clustering might successfully detect similar relations, and provide a valuable preprocessing for semi-supervised approaches.

arXiv:2011.07109

The Teacher-Student Chatroom Corpus

The Teacher-Student Chatroom Corpus (TSCC) is a collection of written conversations captured during one-to-one lessons between teachers and learners of English. The lessons took place in an online chatroom and therefore involve more interactive, immediate and informal language than might be found in asynchronous exchanges such as email correspondence. The fact that the lessons were one-to-one means that the teacher was able to focus exclusively on the linguistic abilities and errors of the student, and to offer personalised exercises, scaffolding and correction. The TSCC contains more than one hundred lessons between two teachers and eight students, amounting to 13.5K conversational turns and 133K words: it is freely available for research use. We describe the corpus design, data collection procedure and annotations added to the text. We perform some preliminary descriptive analyses of the data and consider possible uses of the TSCC.

arXiv:2011.06874

Medical symptom recognition from patient text: An active learning approach for long-tailed multilabel distributions

We study the problem of medical symptoms recognition from patient text, for the purposes of gathering pertinent information from the patient (known as history-taking). A typical patient text is often descriptive of the symptoms the patient is experiencing and a single instance of such a text can be "labeled" with multiple symptoms. This makes learning a medical symptoms recognizer challenging on account of i) the lack of availability of voluminous annotated data as well as ii) the large unknown universe of multiple symptoms that a single text can map to. Furthermore, patient text is often characterized by a long tail in the data (i.e., some labels/symptoms occur more frequently than others for e.g "fever" vs "hematochezia"). In this paper, we introduce an active learning method that leverages underlying structure of a continually refined, learned latent space to select the most informative examples to label. This enables the selection of the most informative examples that progressively increases the coverage on the universe of symptoms via the learned model, despite the long tail in data distribution.

arXiv:2011.04124공식 코드 · Papers with Code

What time is it? Temporal Analysis of Novels

Recognizing the flow of time in a story is a crucial aspect of understanding it. Prior work related to time has primarily focused on identifying temporal expressions or relative sequencing of events, but here we propose computationally annotating each line of a book with wall clock times, even in the absence of explicit time-descriptive phrases. To do so, we construct a data set of hourly time phrases from 52,183 fictional books. We then construct a time-of-day classification model that achieves an average error of 2.27 hours. Furthermore, we show that by analyzing a book in whole using dynamic programming of breakpoints, we can roughly partition a book into segments that each correspond to a particular time-of-day. This approach improves upon baselines by over two hours. Finally, we apply our model to a corpus of literature categorized by different periods in history, to show interesting trends of hourly activity throughout the past. Among several observations we find that the fraction of events taking place past 10 P.M jumps past 1880 - coincident with the advent of the electric light bulb and city lights.

arXiv:2010.10208

Impact of crop diversification on tribal farmer's income: A case study from Eastern ghats of India

In this investigation we analyze impact of diversification of agriculture on farmer's income, a study from primitive tribal groups from eastern ghats of India. We have taken crop diversification index to measure the extent and regression formalism to analyze the impact, of crop diversification. Descriptive statistics is employed to know the average income of the farmers, paired results of crop diversification index. We observed a positive impact on crop diversification in scheduled areas and investigated reasons where it did not work.

arXiv:2011.01385

Dual Attention on Pyramid Feature Maps for Image Captioning

Generating natural sentences from images is a fundamental learning task for visual-semantic understanding in multimedia. In this paper, we propose to apply dual attention on pyramid image feature maps to fully explore the visual-semantic correlations and improve the quality of generated sentences. Specifically, with the full consideration of the contextual information provided by the hidden state of the RNN controller, the pyramid attention can better localize the visually indicative and semantically consistent regions in images. On the other hand, the contextual information can help re-calibrate the importance of feature components by learning the channel-wise dependencies, to improve the discriminative power of visual features for better content description. We conducted comprehensive experiments on three well-known datasets: Flickr8K, Flickr30K and MS COCO, which achieved impressive results in generating descriptive and smooth natural sentences from images. Using either convolution visual features or more informative bottom-up attention features, our composite captioning model achieves very promising performance in a single-model mode. The proposed pyramid attention and dual attention methods are highly modular, which can be inserted into various image captioning modules to further improve the performance.

arXiv:2011.00337

Deep learning in the ultrasound evaluation of neonatal respiratory status

Lung ultrasound imaging is reaching growing interest from the scientific community. On one side, thanks to its harmlessness and high descriptive power, this kind of diagnostic imaging has been largely adopted in sensitive applications, like the diagnosis and follow-up of preterm newborns in neonatal intensive care units. On the other side, state-of-the-art image analysis and pattern recognition approaches have recently proven their ability to fully exploit the rich information contained in these data, making them attractive for the research community. In this work, we present a thorough analysis of recent deep learning networks and training strategies carried out on a vast and challenging multicenter dataset comprising 87 patients with different diseases and gestational ages. These approaches are employed to assess the lung respiratory status from ultrasound images and are evaluated against a reference marker. The conducted analysis sheds some light on this problem by showing the critical points that can mislead the training procedure and proposes some adaptations to the specific data and task. The achieved results sensibly outperform those obtained by a previous work, which is based on textural features, and narrow the gap with the visual score predicted by the human experts.

arXiv:2010.16068

Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification

Relation classification aims to extract semantic relations between entity pairs from the sentences. However, most existing methods can only identify seen relation classes that occurred during training. To recognize unseen relations at test time, we explore the problem of zero-shot relation classification. Previous work regards the problem as reading comprehension or textual entailment, which have to rely on artificial descriptive information to improve the understandability of relation types. Thus, rich semantic knowledge of the relation labels is ignored. In this paper, we propose a novel logic-guided semantic representation learning model for zero-shot relation classification. Our approach builds connections between seen and unseen relations via implicit and explicit semantic representations with knowledge graph embeddings and logic rules. Extensive experimental results demonstrate that our method can generalize to unseen relation types and achieve promising improvements.

arXiv:2010.12596

Effect of Long-Term Debt on the Financial Growth of Non-Financial Firms Listed at the Nairobi Securities Exchange

A significant number of the non-financial firms listed at Nairobi Securities Exchange (NSE) have been experiencing declining financial performance which deter investors from investing in such firms. The lenders are also not willing to lend to such firms. As such, the firms struggle to raise funds for their operations. Prudent financing decisions can lead to financial growth of the firm. The purpose of this study is to assess the effect of Long-term debt on the financial growth of Non-financial firms listed at Nairobi Securities Exchange. Financial firms were excluded because of their specific sector characteristics and stringent regulatory framework. The study is guided by Trade-Off Theory and Theory of Growth of the Firm. Explanatory research design was adopted. The population of the study comprised of 45 non-financial firms listed at the NSE for a period of ten years from 2008 to 2017. The study conducted both descriptive statistics analysis and panel data analysis. The result indicates that Long term debt explains 21.6% and 5.16% of variation in financial growth as measured by growth in earnings per share and growth in market capitalization respectively. Long term debt positively and significantly influences financial growth measured using both growth in earnings per share and growth in market capitalization. The study recommends that, the management of non-financial firms listed at Nairobi Securities Exchange to employ financing means that can improve the earnings per share, market capitalization and enhance the value of the firm for the benefit of its stakeholders.

arXiv:2010.12967

Automated triage of COVID-19 from various lung abnormalities using chest CT features

The outbreak of COVID-19 has lead to a global effort to decelerate the pandemic spread. For this purpose chest computed-tomography (CT) based screening and diagnosis of COVID-19 suspected patients is utilized, either as a support or replacement to reverse transcription-polymerase chain reaction (RT-PCR) test. In this paper, we propose a fully automated AI based system that takes as input chest CT scans and triages COVID-19 cases. More specifically, we produce multiple descriptive features, including lung and infections statistics, texture, shape and location, to train a machine learning based classifier that distinguishes between COVID-19 and other lung abnormalities (including community acquired pneumonia). We evaluated our system on a dataset of 2191 CT cases and demonstrated a robust solution with 90.8% sensitivity at 85.4% specificity with 94.0% ROC-AUC. In addition, we present an elaborated feature analysis and ablation study to explore the importance of each feature.

arXiv:2010.14235공식 코드 · Papers with Code

Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles

Multi-document summarization is a challenging task for which there exists little large-scale datasets. We propose Multi-XScience, a large-scale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challenging multi-document summarization task: writing the related-work section of a paper based on its abstract and the articles it references. Our work is inspired by extreme summarization, a dataset construction protocol that favours abstractive modeling approaches. Descriptive statistics and empirical results---using several state-of-the-art models trained on the Multi-XScience dataset---reveal that Multi-XScience is well suited for abstractive models.

arXiv:2010.11682

Lung Nodule Classification Using Biomarkers, Volumetric Radiomics and 3D CNNs

We present a hybrid algorithm to estimate lung nodule malignancy that combines imaging biomarkers from Radiologist's annotation with image classification of CT scans. Our algorithm employs a 3D Convolutional Neural Network (CNN) as well as a Random Forest in order to combine CT imagery with biomarker annotation and volumetric radiomic features. We analyze and compare the performance of the algorithm using only imagery, only biomarkers, combined imagery + biomarkers, combined imagery + volumetric radiomic features and finally the combination of imagery + biomarkers + volumetric features in order to classify the suspicion level of nodule malignancy. The National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) IDRI dataset is used to train and evaluate the classification task. We show that the incorporation of semi-supervised learning by means of K-Nearest-Neighbors (KNN) can increase the available training sample size of the LIDC-IDRI thereby further improving the accuracy of malignancy estimation of most of the models tested although there is no significant improvement with the use of KNN semi-supervised learning if image classification with CNNs and volumetric features are combined with descriptive biomarkers. Unexpectedly, we also show that a model using image biomarkers alone is more accurate than one that combines biomarkers with volumetric radiomics, 3D CNNs, and semi-supervised learning. We discuss the possibility that this result may be influenced by cognitive bias in LIDC-IDRI because malignancy estimates were recorded by the same radiologist panel as biomarkers, as well as future work to incorporate pathology information over a subset of study participants.

arXiv:2010.09009

Image-based Automated Species Identification: Can Virtual Data Augmentation Overcome Problems of Insufficient Sampling?

Automated species identification and delimitation is challenging, particularly in rare and thus often scarcely sampled species, which do not allow sufficient discrimination of infraspecific versus interspecific variation. Typical problems arising from either low or exaggerated interspecific morphological differentiation are best met by automated methods of machine learning that learn efficient and effective species identification from training samples. However, limited infraspecific sampling remains a key challenge also in machine learning. 1In this study, we assessed whether a two-level data augmentation approach may help to overcome the problem of scarce training data in automated visual species identification. The first level of visual data augmentation applies classic approaches of data augmentation and generation of faked images using a GAN approach. Descriptive feature vectors are derived from bottleneck features of a VGG-16 convolutional neural network (CNN) that are then stepwise reduced in dimensionality using Global Average Pooling and PCA to prevent overfitting. The second level of data augmentation employs synthetic additional sampling in feature space by an oversampling algorithm in vector space (SMOTE). Applied on two challenging datasets of scarab beetles (Coleoptera), our augmentation approach outperformed a non-augmented deep learning baseline approach as well as a traditional 2D morphometric approach (Procrustes analysis).

arXiv:2010.09079공식 코드 · Papers with Code

Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration

3D Point clouds are a rich source of information that enjoy growing popularity in the vision community. However, due to the sparsity of their representation, learning models based on large point clouds is still a challenge. In this work, we introduce Graphite, a GRAPH-Induced feaTure Extraction pipeline, a simple yet powerful feature transform and keypoint detector. Graphite enables intensive down-sampling of point clouds with keypoint detection accompanied by a descriptor. We construct a generic graph-based learning scheme to describe point cloud regions and extract salient points. To this end, we take advantage of 6D pose information and metric learning to learn robust descriptions and keypoints across different scans. We Reformulate the 3D keypoint pipeline with graph neural networks which allow efficient processing of the point set while boosting its descriptive power which ultimately results in more accurate 3D registrations. We demonstrate our lightweight descriptor on common 3D descriptor matching and point cloud registration benchmarks and achieve comparable results with the state of the art. Describing 100 patches of a point cloud and detecting their keypoints takes only ~0.018 seconds with our proposed network.

arXiv:2010.06186

Correlation-wise Smoothing: Lightweight Knowledge Extraction for HPC Monitoring Data

Modern High-Performance Computing (HPC) and data center operators rely more and more on data analytics techniques to improve the efficiency and reliability of their operations. They employ models that ingest time-series monitoring sensor data and transform it into actionable knowledge for system tuning: a process known as Operational Data Analytics (ODA). However, monitoring data has a high dimensionality, is hardware-dependent and difficult to interpret. This, coupled with the strict requirements of ODA, makes most traditional data mining methods impractical and in turn renders this type of data cumbersome to process. Most current ODA solutions use ad-hoc processing methods that are not generic, are sensible to the sensors' features and are not fit for visualization. In this paper we propose a novel method, called Correlation-wise Smoothing (CS), to extract descriptive signatures from time-series monitoring data in a generic and lightweight way. Our CS method exploits correlations between data dimensions to form groups and produces image-like signatures that can be easily manipulated, visualized and compared. We evaluate the CS method on HPC-ODA, a collection of datasets that we release with this work, and show that it leads to the same performance as most state-of-the-art methods while producing signatures that are up to ten times smaller and up to ten times faster, while gaining visualizability, portability across systems and clear scaling properties.