PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2109.04304

DAE-PINN: A Physics-Informed Neural Network Model for Simulating Differential-Algebraic Equations with Application to Power Networks

Deep learning-based surrogate modeling is becoming a promising approach for learning and simulating dynamical systems. Deep-learning methods, however, find very challenging learning stiff dynamics. In this paper, we develop DAE-PINN, the first effective deep-learning framework for learning and simulating the solution trajectories of nonlinear differential-algebraic equations (DAE), which present a form of infinite stiffness and describe, for example, the dynamics of power networks. Our DAE-PINN bases its effectiveness on the synergy between implicit Runge-Kutta time-stepping schemes (designed specifically for solving DAEs) and physics-informed neural networks (PINN) (deep neural networks that we train to satisfy the dynamics of the underlying problem). Furthermore, our framework (i) enforces the neural network to satisfy the DAEs as (approximate) hard constraints using a penalty-based method and (ii) enables simulating DAEs for long-time horizons. We showcase the effectiveness and accuracy of DAE-PINN by learning and simulating the solution trajectories of a three-bus power network.

arXiv:2109.04081

DeepEMO: Deep Learning for Speech Emotion Recognition

We proposed the industry level deep learning approach for speech emotion recognition task. In industry, carefully proposed deep transfer learning technology shows real results due to mostly low amount of training data availability, machine training cost, and specialized learning on dedicated AI tasks. The proposed speech recognition framework, called DeepEMO, consists of two main pipelines such that preprocessing to extract efficient main features and deep transfer learning model to train and recognize. Main source code is in https://github.com/enkhtogtokh/deepemo repository

arXiv:2109.03992

Stationary Density Estimation of Itô Diffusions Using Deep Learning

In this paper, we consider the density estimation problem associated with the stationary measure of ergodic It\^o diffusions from a discrete-time series that approximate the solutions of the stochastic differential equations. To take an advantage of the characterization of density function through the stationary solution of a parabolic-type Fokker-Planck PDE, we proceed as follows. First, we employ deep neural networks to approximate the drift and diffusion terms of the SDE by solving appropriate supervised learning tasks. Subsequently, we solve a steady-state Fokker-Plank equation associated with the estimated drift and diffusion coefficients with a neural-network-based least-squares method. We establish the convergence of the proposed scheme under appropriate mathematical assumptions, accounting for the generalization errors induced by regressing the drift and diffusion coefficients, and the PDE solvers. This theoretical study relies on a recent perturbation theory of Markov chain result that shows a linear dependence of the density estimation to the error in estimating the drift term, and generalization error results of nonparametric regression and of PDE regression solution obtained with neural-network models. The effectiveness of this method is reflected by numerical simulations of a two-dimensional Student's t distribution and a 20-dimensional Langevin dynamics.

arXiv:2109.04392공식 코드 · Papers with Code

Fair Conformal Predictors for Applications in Medical Imaging

Deep learning has the potential to automate many clinically useful tasks in medical imaging. However translation of deep learning into clinical practice has been hindered by issues such as lack of the transparency and interpretability in these "black box" algorithms compared to traditional statistical methods. Specifically, many clinical deep learning models lack rigorous and robust techniques for conveying certainty (or lack thereof) in their predictions -- ultimately limiting their appeal for extensive use in medical decision-making. Furthermore, numerous demonstrations of algorithmic bias have increased hesitancy towards deployment of deep learning for clinical applications. To this end, we explore how conformal predictions can complement existing deep learning approaches by providing an intuitive way of expressing uncertainty while facilitating greater transparency to clinical users. In this paper, we conduct field interviews with radiologists to assess possible use-cases for conformal predictors. Using insights gathered from these interviews, we devise two clinical use-cases and empirically evaluate several methods of conformal predictions on a dermatology photography dataset for skin lesion classification. We show how to modify conformal predictions to be more adaptive to subgroup differences in patient skin tones through equalized coverage. Finally, we compare conformal prediction against measures of epistemic uncertainty.

arXiv:2109.03661

Single Plane-Wave Imaging using Physics-Based Deep Learning

In plane-wave imaging, multiple unfocused ultrasound waves are transmitted into a medium of interest from different angles and an image is formed from the recorded reflections. The number of plane waves used leads to a trade-off between frame-rate and image quality, with single-plane-wave (SPW) imaging being the fastest possible modality with the worst image quality. Recently, deep learning methods have been proposed to improve ultrasound imaging. One approach is to use image-to-image networks that work on the formed image and another is to directly learn a mapping from data to an image. Both approaches utilize purely data-driven models and require deep, expressive network architectures, combined with large numbers of training samples to obtain good results. Here, we propose a data-to-image architecture that incorporates a wave-physics-based image formation algorithm in-between deep convolutional neural networks. To achieve this, we implement the Fourier (FK) migration method as network layers and train the whole network end-to-end. We compare our proposed data-to-image network with an image-to-image network in simulated data experiments, mimicking a medical ultrasound application. Experiments show that it is possible to obtain high-quality SPW images, almost similar to an image formed using 75 plane waves over an angular range of $\pm$16$^\circ$. This illustrates the great potential of combining deep neural networks with physics-based image formation algorithms for SPW imaging.

arXiv:2109.03616

Deep Learning for Multi-View Ultrasonic Image Fusion

Ultrasonic imaging is being used to obtain information about the acoustic properties of a medium by emitting waves into it and recording their interaction using ultrasonic transducer arrays. The Delay-And-Sum (DAS) algorithm forms images using the main path on which reflected signals travel back to the transducers. In some applications, different insonification paths can be considered, for instance by placing the transducers at different locations or if strong reflectors inside the medium are known a-priori. These different modes give rise to multiple DAS images reflecting different geometric information about the scatterers and the challenge is to either fuse them into one image or to directly extract higher-level information regarding the materials of the medium, e.g., a segmentation map. Traditional image fusion techniques typically use ad-hoc combinations of pre-defined image transforms, pooling operations and thresholding. In this work, we propose a deep neural network (DNN) architecture that directly maps all available data to a segmentation map while explicitly incorporating the DAS image formation for the different insonification paths as network layers. This enables information flow between data pre-processing and image post-processing DNNs, trained end-to-end. We compare our proposed method to a traditional image fusion technique using simulated data experiments, mimicking a non-destructive testing application with four image modes, i.e., two transducer locations and two internal reflection boundaries. Using our approach, it is possible to obtain much more accurate segmentation of defects.

arXiv:2109.03465

A Survey of Sound Source Localization with Deep Learning Methods

This article is a survey on deep learning methods for single and multiple sound source localization. We are particularly interested in sound source localization in indoor/domestic environment, where reverberation and diffuse noise are present. We provide an exhaustive topography of the neural-based localization literature in this context, organized according to several aspects: the neural network architecture, the type of input features, the output strategy (classification or regression), the types of data used for model training and evaluation, and the model training strategy. This way, an interested reader can easily comprehend the vast panorama of the deep learning-based sound source localization methods. Tables summarizing the literature survey are provided at the end of the paper for a quick search of methods with a given set of target characteristics.

arXiv:2109.03389

An Optimal Resource Allocator of Elastic Training for Deep Learning Jobs on Cloud

Cloud training platforms, such as Amazon Web Services and Huawei Cloud provide users with computational resources to train their deep learning jobs. Elastic training is a service embedded in cloud training platforms that dynamically scales up or down the resources allocated to a job. The core technique of an elastic training system is to best allocate limited resources among heterogeneous jobs in terms of shorter queueing delay and higher training efficiency. This paper presents an optimal resource allocator for elastic training system that leverages a mixed-integer programming (MIP) model to maximize the training progress of deep learning jobs. We take advantage of the real-world job data obtained from ModelArts, the deep learning training platform of Huawei Cloud and conduct simulation experiments to compare the optimal resource allocator with a greedy one as benchmark. Numerical results show that the proposed allocator can reduce queuing time by up to 32% and accelerate training efficiency by up to 24% relative to the greedy resource allocator, thereby greatly improving user experience with Huawei ModelArts and potentially enabling the realization of higher profits for the product. Also, the optimal resource allocator is fast in decision-making, taking merely 0.4 seconds on average.

arXiv:2109.03710

BotSpot: Deep Learning Classification of Bot Accounts within Twitter

The openness feature of Twitter allows programs to generate and control Twitter accounts automatically via the Twitter API. These accounts, which are known as bots, can automatically perform actions such as tweeting, re-tweeting, following, unfollowing, or direct messaging other accounts, just like real people. They can also conduct malicious tasks such as spreading of fake news, spams, malicious software and other cyber-crimes. In this paper, we introduce a novel bot detection approach using deep learning, with the Multi-layer Perceptron Neural Networks and nine features of a bot account. A web crawler is developed to automatically collect data from public Twitter accounts and build the testing and training datasets, with 860 samples of human and bot accounts. After the initial training is done, the Multilayer Perceptron Neural Networks achieved an overall accuracy rate of 92%, which proves the performance of the proposed approach.

arXiv:2109.02441

Application of Monte Carlo Stochastic Optimization (MOST) to Deep Learning

In this paper, we apply the Monte Carlo stochastic optimization (MOST) proposed by the authors to a deep learning of XOR gate and verify its effectiveness. Deep machine learning based on neural networks is one of the most important keywords driving innovation in today's highly advanced information society. Therefore, there has been active research on large-scale, high-speed, and high-precision systems. For the purpose of efficiently searching the optimum value of the objective function, the author divides the search region of a multivariable parameter constituting the objective function into two by each parameter, numerically finds the integration of the two regions by the Monte Carlo method, compares the magnitude of the integration value, and judges that there is an optimum point in a small region. In the previous paper, we examined the problem of the benchmark in the optimization method. This method is applied to neural networks of XOR gate, and compared with the results of weight factor optimization by Adam and genetic algorithm. As a result, it was confirmed that it converged faster than the existing method.

arXiv:2109.02532

Automated Robustness with Adversarial Training as a Post-Processing Step

Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging. As a step towards practical automation, this work explores the efficacy of a simple post processing step in yielding robust deep learning model. To achieve this, we adopt adversarial training as a post-processing step for optimised network architectures obtained from a neural architecture search algorithm. Specific policies are adopted for tuning the hyperparameters of the different steps, resulting in a fully automated pipeline for generating adversarially robust deep learning models. We evidence the usefulness of the proposed pipeline with extensive experimentation across 11 image classification and 9 text classification tasks.

arXiv:2109.01954공식 코드 · Papers with Code

An Exploration of Deep Learning Methods in Hungry Geese

Hungry Geese is a n-player variation of the popular game snake. This paper looks at state of the art Deep Reinforcement Learning Value Methods. The goal of the paper is to aggregate research of value based methods and apply it as an exercise to other environments. A vanilla Deep Q Network, a Double Q-network and a Dueling Q-Network were all examined and tested with the Hungry Geese environment. The best performing model was the vanilla Deep Q Network due to its simple state representation and smaller network structure. Converging towards an optimal policy was found to be difficult due to random geese initialization and food generation. Therefore we show that Deep Q Networks may not be the appropriate model for such a stochastic environment and lastly we present improvements that can be made along with more suitable models for the environment.

arXiv:2109.01441

Style Transfer based Coronary Artery Segmentation in X-ray Angiogram

X-ray coronary angiography (XCA) is a principal approach employed for identifying coronary disorders. Deep learning-based networks have recently shown tremendous promise in the diagnosis of coronary disorder from XCA scans. A deep learning-based edge adaptive instance normalization style transfer technique for segmenting the coronary arteries, is presented in this paper. The proposed technique combines adaptive instance normalization style transfer with the dense extreme inception network and convolution block attention module to get the best artery segmentation performance. We tested the proposed method on two publicly available XCA datasets, and achieved a segmentation accuracy of 0.9658 and Dice coefficient of 0.71. We believe that the proposed method shows that the prediction can be completed in the fastest time with training on the natural images, and can be reliably used to diagnose and detect coronary disorders.

arXiv:2109.01351

MitoVis: A Visually-guided Interactive Intelligent System for Neuronal Mitochondria Analysis

Neurons have a polarized structure, including dendrites and axons, and compartment-specific functions can be affected by dwelling mitochondria. It is known that the morphology of mitochondria is closely related to the functions of neurons and neurodegenerative diseases. Even though several deep learning methods have been developed to automatically analyze the morphology of mitochondria, the application of existing methods to actual analysis still encounters several difficulties. Since the performance of pre-trained deep learning model may vary depending on the target data, re-training of the model is often required. Besides, even though deep learning has shown superior performance under a constrained setup, there are always errors that need to be corrected by humans in real analysis. To address these issues, we introduce MitoVis, a novel visualization system for end-to-end data processing and interactive analysis of the morphology of neuronal mitochondria. MitoVis enables interactive fine-tuning of a pre-trained neural network model without the domain knowledge of machine learning, which allows neuroscientists to easily leverage deep learning in their research. MitoVis also provides novel visual guides and interactive proofreading functions so that the users can quickly identify and correct errors in the result with minimal effort. We demonstrate the usefulness and efficacy of the system via a case study conducted by a neuroscientist on a real analysis scenario. The result shows that MitoVis allows up to 15x faster analysis with similar accuracy compared to the fully manual analysis method.

arXiv:2109.01236

Non-intrusive load decomposition based on CNN-LSTM hybrid deep learning model

With the rapid development of science and technology, the problem of energy load monitoring and decomposition of electrical equipment has been receiving widespread attention from academia and industry. For the purpose of improving the performance of non-intrusive load decomposition, a non-intrusive load decomposition method based on a hybrid deep learning model is proposed. In this method, first of all, the data set is normalized and preprocessed. Secondly, a hybrid deep learning model integrating convolutional neural network (CNN) with long short-term memory network (LSTM) is constructed to fully excavate the spatial and temporal characteristics of load data. Finally, different evaluation indicators are used to analyze the mixture. The model is fully evaluated, and contrasted with the traditional single deep learning model. Experimental results on the open dataset UK-DALE show that the proposed algorithm improves the performance of the whole network system. In this paper, the proposed decomposition method is compared with the existing traditional deep learning load decomposition method. At the same time, compared with the obtained methods: spectral decomposition, EMS, LSTM-RNN, and other algorithms, the accuracy of load decomposition is significantly improved, and the test accuracy reaches 98%.

arXiv:2109.01376

Deep Learning for Fitness

We present Fitness tutor, an application for maintaining correct posture during workout exercises or doing yoga. Current work on fitness focuses on suggesting food supplements, accessing workouts, workout wearables does a great job in improving the fitness. Meanwhile, the current situation is making difficult to monitor workouts by trainee. Inspired by healthcare innovations like robotic surgery, we design a novel application Fitness tutor which can guide the workouts using pose estimation. Pose estimation can be deployed on the reference image for gathering data and guide the user with the data. This allow Fitness tutor to guide the workouts (both exercise and yoga) in remote conditions with a single reference posture as image. We use posenet model in tensorflow with p5js for developing skeleton. Fitness tutor is an application of pose estimation model in bringing a realtime teaching experience in fitness. Our experiments shows that it can leverage potential of pose estimation models by providing guidance in realtime.

arXiv:2109.00924

Parallel Multi-Graph Convolution Network For Metro Passenger Volume Prediction

Accurate prediction of metro passenger volume (number of passengers) is valuable to realize real-time metro system management, which is a pivotal yet challenging task in intelligent transportation. Due to the complex spatial correlation and temporal variation of urban subway ridership behavior, deep learning has been widely used to capture non-linear spatial-temporal dependencies. Unfortunately, the current deep learning methods only adopt graph convolutional network as a component to model spatial relationship, without making full use of the different spatial correlation patterns between stations. In order to further improve the accuracy of metro passenger volume prediction, a deep learning model composed of Parallel multi-graph convolution and stacked Bidirectional unidirectional Gated Recurrent Unit (PB-GRU) was proposed in this paper. The parallel multi-graph convolution captures the origin-destination (OD) distribution and similar flow pattern between the metro stations, while bidirectional gated recurrent unit considers the passenger volume sequence in forward and backward directions and learns complex temporal features. Extensive experiments on two real-world datasets of subway passenger flow show the efficacy of the model. Surprisingly, compared with the existing methods, PB-GRU achieves much lower prediction error.

arXiv:2109.00594

Wearable-based Classification of Running Styles with Deep Learning

Automatic classification of running styles can enable runners to obtain feedback with the aim of optimizing performance in terms of minimizing energy expenditure, fatigue, and risk of injury. To develop a system capable of classifying running styles using wearables, we collect a dataset from 10 healthy runners performing 8 different pre-defined running styles. Five wearable devices are used to record accelerometer data from different parts of the lower body, namely left and right foot, left and right medial tibia, and lower back. Using the collected dataset, we develop a deep learning solution which consists of a Convolutional Neural Network and Long Short-Term Memory network to first automatically extract effective features, followed by learning temporal relationships. Score-level fusion is used to aggregate the classification results from the different sensors. Experiments show that the proposed model is capable of automatically classifying different running styles in a subject-dependant manner, outperforming several classical machine learning methods (following manual feature extraction) and a convolutional neural network baseline. Moreover, our study finds that subject-independent classification of running styles is considerably more challenging than a subject-dependant scheme, indicating a high level of personalization in such running styles. Finally, we demonstrate that by fine-tuning the model with as few as 5% subject-specific samples, considerable performance boost is obtained.

arXiv:2109.00347

A survey on IQA

Image quality assessment(IQA) is of increasing importance for image-based applications. Its purpose is to establish a model that can replace humans for accurately evaluating image quality. According to whether the reference image is complete and available, image quality evaluation can be divided into three categories: full-reference(FR), reduced-reference(RR), and non-reference(NR) image quality assessment. Due to the vigorous development of deep learning and the widespread attention of researchers, several non-reference image quality assessment methods based on deep learning have been proposed in recent years, and some have exceeded the performance of reduced -reference or even full-reference image quality assessment models. This article will review the concepts and metrics of image quality assessment and also video quality assessment, briefly introduce some methods of full-reference and semi-reference image quality assessment, and focus on the non-reference image quality assessment methods based on deep learning. Then introduce the commonly used synthetic database and real-world database. Finally, summarize and present challenges.