PyTorchKR Papers

최신 논문

총 2,063편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2210.05240공식 코드 · Papers with Code

Multi-site Diagnostic Classification Of Schizophrenia Using 3D CNN On Aggregated Task-based fMRI Data

In spite of years of research, the mechanisms that underlie the development of schizophrenia, as well as its relapse, symptomatology, and treatment, continue to be a mystery. The absence of appropriate analytic tools to deal with the variable and complicated nature of schizophrenia may be one of the factors that contribute to the development of this disorder. Deep learning is a subfield of artificial intelligence that was inspired by the nervous system. In recent years, deep learning has made it easier to model and analyse complicated, high-dimensional, and nonlinear systems. Research on schizophrenia is one of the many areas of study that has been revolutionised as a result of the outstanding accuracy that deep learning algorithms have demonstrated in classification and prediction tasks. Deep learning has the potential to become a powerful tool for understanding the mechanisms that are at the root of schizophrenia. In addition, a growing variety of techniques aimed at improving model interpretability and causal reasoning are contributing to this trend. Using multi-site fMRI data and a variety of deep learning approaches, this study seeks to identify different types of schizophrenia. Our proposed method of temporal aggregation of the 4D fMRI data outperforms existing work. In addition, this study aims to shed light on the strength of connections between various brain areas in schizophrenia individuals.

arXiv:2210.04323공식 코드 · Papers with Code

Deep Learning Inference Frameworks Benchmark

Deep learning (DL) has been widely adopted those last years but they are computing-intensive method. Therefore, scientists proposed diverse optimization to accelerate their predictions for end-user applications. However, no single inference framework currently dominates in terms of performance. This paper takes a holistic approach to conduct an empirical comparison and analysis of four representative DL inference frameworks. First, given a selection of CPU-GPU configurations, we show that for a specific DL framework, different configurations of its settings may have a significant impact on the prediction speed, memory, and computing power. Second, to the best of our knowledge, this study is the first to identify the opportunities for accelerating the ensemble of co-localized models in the same GPU. This measurement study provides an in-depth empirical comparison and analysis of four representative DL frameworks and offers practical guidance for service providers to deploy and deliver DL predictions.

arXiv:2210.04389공식 코드 · Papers with Code

DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning

Causal mediation analysis can unpack the black box of causality and is therefore a powerful tool for disentangling causal pathways in biomedical and social sciences, and also for evaluating machine learning fairness. To reduce bias for estimating Natural Direct and Indirect Effects in mediation analysis, we propose a new method called DeepMed that uses deep neural networks (DNNs) to cross-fit the infinite-dimensional nuisance functions in the efficient influence functions. We obtain novel theoretical results that our DeepMed method (1) can achieve semiparametric efficiency bound without imposing sparsity constraints on the DNN architecture and (2) can adapt to certain low dimensional structures of the nuisance functions, significantly advancing the existing literature on DNN-based semiparametric causal inference. Extensive synthetic experiments are conducted to support our findings and also expose the gap between theory and practice. As a proof of concept, we apply DeepMed to analyze two real datasets on machine learning fairness and reach conclusions consistent with previous findings.

arXiv:2210.04104공식 코드 · Papers with Code

Training Deep Learning Algorithms on Synthetic Forest Images for Tree Detection

Vision-based segmentation in forested environments is a key functionality for autonomous forestry operations such as tree felling and forwarding. Deep learning algorithms demonstrate promising results to perform visual tasks such as object detection. However, the supervised learning process of these algorithms requires annotations from a large diversity of images. In this work, we propose to use simulated forest environments to automatically generate 43 k realistic synthetic images with pixel-level annotations, and use it to train deep learning algorithms for tree detection. This allows us to address the following questions: i) what kind of performance should we expect from deep learning in harsh synthetic forest environments, ii) which annotations are the most important for training, and iii) what modality should be used between RGB and depth. We also report the promising transfer learning capability of features learned on our synthetic dataset by directly predicting bounding box, segmentation masks and keypoints on real images. Code available on GitHub (https://github.com/norlab-ulaval/PercepTreeV1).

arXiv:2210.03258공식 코드 · Papers with Code

Interpreting County Level COVID-19 Infection and Feature Sensitivity using Deep Learning Time Series Models

Interpretable machine learning plays a key role in healthcare because it is challenging in understanding feature importance in deep learning model predictions. We propose a novel framework that uses deep learning to study feature sensitivity for model predictions. This work combines sensitivity analysis with heterogeneous time-series deep learning model prediction, which corresponds to the interpretations of spatio-temporal features. We forecast county-level COVID-19 infection using the Temporal Fusion Transformer. We then use the sensitivity analysis extending Morris Method to see how sensitive the outputs are with respect to perturbation to our static and dynamic input features. The significance of the work is grounded in a real-world COVID-19 infection prediction with highly non-stationary, finely granular, and heterogeneous data. 1) Our model can capture the detailed daily changes of temporal and spatial model behaviors and achieves high prediction performance compared to a PyTorch baseline. 2) By analyzing the Morris sensitivity indices and attention patterns, we decipher the meaning of feature importance with observational population and dynamic model changes. 3) We have collected 2.5 years of socioeconomic and health features over 3142 US counties, such as observed cases and deaths, and a number of static (age distribution, health disparity, and industry) and dynamic features (vaccination, disease spread, transmissible cases, and social distancing). Using the proposed framework, we conduct extensive experiments and show our model can learn complex interactions and perform predictions for daily infection at the county level. Being able to model the disease infection with a hybrid prediction and description accuracy measurement with Morris index at the county level is a central idea that sheds light on individual feature interpretation via sensitivity analysis.

arXiv:2210.02675공식 코드 · Papers with Code

Look Ma, Only 400 Samples! Revisiting the Effectiveness of Automatic N-Gram Rule Generation for Spelling Normalization in Filipino

With 84.75 million Filipinos online, the ability for models to process online text is crucial for developing Filipino NLP applications. To this end, spelling correction is a crucial preprocessing step for downstream processing. However, the lack of data prevents the use of language models for this task. In this paper, we propose an N-Gram + Damerau Levenshtein distance model with automatic rule extraction. We train the model on 300 samples, and show that despite limited training data, it achieves good performance and outperforms other deep learning approaches in terms of accuracy and edit distance. Moreover, the model (1) requires little compute power, (2) trains in little time, thus allowing for retraining, and (3) is easily interpretable, allowing for direct troubleshooting, highlighting the success of traditional approaches over more complex deep learning models in settings where data is unavailable.

arXiv:2210.02339공식 코드 · Papers with Code

Particle clustering in turbulence: Prediction of spatial and statistical properties with deep learning

We investigate the utility of deep learning for modeling the clustering of particles that are aerodynamically coupled to turbulent fluids. Using a Lagrangian particle module within the Athena++ hydrodynamics code, we simulate the dynamics of particles in the Epstein drag regime within a periodic domain of isotropic forced hydrodynamic turbulence. This setup is an idealized model relevant to the collisional growth of micron to mm-sized dust particles in early stage planet formation. The simulation data are used to train a U-Net deep learning model to predict gridded three-dimensional representations of the particle density and velocity fields, given as input the corresponding fluid fields. The trained model qualitatively captures the filamentary structure of clustered particles in a highly non-linear regime. We assess model fidelity by calculating metrics of the density field (the radial distribution function) and of the velocity field (the relative velocity and the relative radial velocity between particles). Although trained only on the spatial fields, the model predicts these statistical quantities with errors that are typically <10%. Our results suggest that, given appropriately expanded training data, deep learning could complement direct numerical simulations in predicting particle clustering within turbulent flows.

arXiv:2210.00222공식 코드 · Papers with Code

Solving Coupled Differential Equation Groups Using PINO-CDE

As a fundamental mathmatical tool in many engineering disciplines, coupled differential equation groups are being widely used to model complex structures containing multiple physical quantities. Engineers constantly adjust structural parameters at the design stage, which requires a highly efficient solver. The rise of deep learning technologies has offered new perspectives on this task. Unfortunately, existing black-box models suffer from poor accuracy and robustness, while the advanced methodologies of single-output operator regression cannot deal with multiple quantities simultaneously. To address these challenges, we propose PINO-CDE, a deep learning framework for solving coupled differential equation groups (CDEs) along with an equation normalization algorithm for performance enhancing. Based on the theory of physics-informed neural operator (PINO), PINO-CDE uses a single network for all quantities in a CDEs, instead of training dozens, or even hundreds of networks as in the existing literature. We demonstrate the flexibility and feasibility of PINO-CDE for one toy example and two engineering applications: vehicle-track coupled dynamics (VTCD) and reliability assessment for a four-storey building (uncertainty propagation). The performance of VTCD indicates that PINO-CDE outperforms existing software and deep learning-based methods in terms of efficiency and precision, respectively. For the uncertainty propagation task, PINO-CDE provides higher-resolution results in less than a quarter of the time incurred when using the probability density evolution method (PDEM). This framework integrates engineering dynamics and deep learning technologies and may reveal a new concept for CDEs solving and uncertainty propagation.

arXiv:2209.14907공식 코드 · Papers with Code

Patients' Severity States Classification based on Electronic Health Record (EHR) Data using Multiple Machine Learning and Deep Learning Approaches

This research presents an examination of categorizing the severity states of patients based on their electronic health records during a certain time range using multiple machine learning and deep learning approaches. The suggested method uses an EHR dataset collected from an open-source platform to categorize severity. Some tools were used in this research, such as openRefine was used to pre-process, RapidMiner was used for implementing three algorithms (Fast Large Margin, Generalized Linear Model, Multi-layer Feed-forward Neural Network) and Tableau was used to visualize the data, for implementation of algorithms we used Google Colab. Here we implemented several supervised and unsupervised algorithms along with semi-supervised and deep learning algorithms. The experimental results reveal that hyperparameter-tuned Random Forest outperformed all the other supervised machine learning algorithms with 76% accuracy as well as Generalized Linear algorithm achieved the highest precision score 78%, whereas the hyperparameter-tuned Hierarchical Clustering with 86% precision score and Gaussian Mixture Model with 61% accuracy outperformed other unsupervised approaches. Dimensionality Reduction improved results a lot for most unsupervised techniques. For implementing Deep Learning we employed a feed-forward neural network (multi-layer) and the Fast Large Margin approach for semi-supervised learning. The Fast Large Margin performed really well with a recall score of 84% and an F1 score of 78%. Finally, the Multi-layer Feed-forward Neural Network performed admirably with 75% accuracy, 75% precision, 87% recall, 81% F1 score.

arXiv:2209.13877공식 코드 · Papers with Code

YATO: Yet Another deep learning based Text analysis Open toolkit

We introduce YATO, an open-source, easy-to-use toolkit for text analysis with deep learning. Different from existing heavily engineered toolkits and platforms, YATO is lightweight and user-friendly for researchers from cross-disciplinary areas. Designed in a hierarchical structure, YATO supports free combinations of three types of widely used features including 1) traditional neural networks (CNN, RNN, etc.); 2) pre-trained language models (BERT, RoBERTa, ELECTRA, etc.); and 3) user-customized neural features via a simple configurable file. Benefiting from the advantages of flexibility and ease of use, YATO can facilitate fast reproduction and refinement of state-of-the-art NLP models, and promote the cross-disciplinary applications of NLP techniques. The code, examples, and documentation are publicly available at https://github.com/jiesutd/YATO. A demo video is also available at https://www.youtube.com/playlist?list=PLJ0mhzMcRuDUlTkzBfAftOqiJRxYTTjXH.

arXiv:2209.13435공식 코드 · Papers with Code

Scaling Laws For Deep Learning Based Image Reconstruction

Deep neural networks trained end-to-end to map a measurement of a (noisy) image to a clean image perform excellent for a variety of linear inverse problems. Current methods are only trained on a few hundreds or thousands of images as opposed to the millions of examples deep networks are trained on in other domains. In this work, we study whether major performance gains are expected from scaling up the training set size. We consider image denoising, accelerated magnetic resonance imaging, and super-resolution and empirically determine the reconstruction quality as a function of training set size, while simultaneously scaling the network size. For all three tasks we find that an initially steep power-law scaling slows significantly already at moderate training set sizes. Interpolating those scaling laws suggests that even training on millions of images would not significantly improve performance. To understand the expected behavior, we analytically characterize the performance of a linear estimator learned with early stopped gradient descent. The result formalizes the intuition that once the error induced by learning the signal model is small relative to the error floor, more training examples do not improve performance.

arXiv:2209.12299공식 코드 · Papers with Code

WARC-DL: Scalable Web Archive Processing for Deep Learning

Web archives have grown to petabytes. In addition to providing invaluable background knowledge on many social and cultural developments over the last 30 years, they also provide vast amounts of training data for machine learning. To benefit from recent developments in Deep Learning, the use of web archives requires a scalable solution for their processing that supports inference with and training of neural networks. To date, there is no publicly available library for processing web archives in this way, and some existing applications use workarounds. This paper presents WARC-DL, a deep learning-enabled pipeline for web archive processing that scales to petabytes.

arXiv:2209.11883공식 코드 · Papers with Code

Hebbian Deep Learning Without Feedback

Recent approximations to backpropagation (BP) have mitigated many of BP's computational inefficiencies and incompatibilities with biology, but important limitations still remain. Moreover, the approximations significantly decrease accuracy in benchmarks, suggesting that an entirely different approach may be more fruitful. Here, grounded on recent theory for Hebbian learning in soft winner-take-all networks, we present multilayer SoftHebb, i.e. an algorithm that trains deep neural networks, without any feedback, target, or error signals. As a result, it achieves efficiency by avoiding weight transport, non-local plasticity, time-locking of layer updates, iterative equilibria, and (self-) supervisory or other feedback signals -- which were necessary in other approaches. Its increased efficiency and biological compatibility do not trade off accuracy compared to state-of-the-art bio-plausible learning, but rather improve it. With up to five hidden layers and an added linear classifier, accuracies on MNIST, CIFAR-10, STL-10, and ImageNet, respectively reach 99.4%, 80.3%, 76.2%, and 27.3%. In conclusion, SoftHebb shows with a radically different approach from BP that Deep Learning over few layers may be plausible in the brain and increases the accuracy of bio-plausible machine learning. Code is available at https://github.com/NeuromorphicComputing/SoftHebb.

arXiv:2209.12128공식 코드 · Papers with Code

A Deep Learning Approach to Analyzing Continuous-Time Systems

Scientists often use observational time series data to study complex natural processes, but regression analyses often assume simplistic dynamics. Recent advances in deep learning have yielded startling improvements to the performance of models of complex processes, but deep learning is generally not used for scientific analysis. Here we show that deep learning can be used to analyze complex processes, providing flexible function approximation while preserving interpretability. Our approach relaxes standard simplifying assumptions (e.g., linearity, stationarity, and homoscedasticity) that are implausible for many natural systems and may critically affect the interpretation of data. We evaluate our model on incremental human language processing, a domain with complex continuous dynamics. We demonstrate substantial improvements on behavioral and neuroimaging data, and we show that our model enables discovery of novel patterns in exploratory analyses, controls for diverse confounds in confirmatory analyses, and opens up research questions that are otherwise hard to study.

arXiv:2209.11064공식 코드 · Papers with Code

Deep Learning on Home Drone: Searching for the Optimal Architecture

We suggest the first system that runs real-time semantic segmentation via deep learning on a weak micro-computer such as the Raspberry Pi Zero v2 (whose price was \$15) attached to a toy-drone. In particular, since the Raspberry Pi weighs less than $16$ grams, and its size is half of a credit card, we could easily attach it to the common commercial DJI Tello toy-drone (<\$100, <90 grams, 98 $\times$ 92.5 $\times$ 41 mm). The result is an autonomous drone (no laptop nor human in the loop) that can detect and classify objects in real-time from a video stream of an on-board monocular RGB camera (no GPS or LIDAR sensors). The companion videos demonstrate how this Tello drone scans the lab for people (e.g. for the use of firefighters or security forces) and for an empty parking slot outside the lab. Existing deep learning solutions are either much too slow for real-time computation on such IoT devices, or provide results of impractical quality. Our main challenge was to design a system that takes the best of all worlds among numerous combinations of networks, deep learning platforms/frameworks, compression techniques, and compression ratios. To this end, we provide an efficient searching algorithm that aims to find the optimal combination which results in the best tradeoff between the network running time and its accuracy/performance.

arXiv:2209.10785공식 코드 · Papers with Code

Deep Lake: a Lakehouse for Deep Learning

Traditional data lakes provide critical data infrastructure for analytical workloads by enabling time travel, running SQL queries, ingesting data with ACID transactions, and visualizing petabyte-scale datasets on cloud storage. They allow organizations to break down data silos, unlock data-driven decision-making, improve operational efficiency, and reduce costs. However, as deep learning usage increases, traditional data lakes are not well-designed for applications such as natural language processing (NLP), audio processing, computer vision, and applications involving non-tabular datasets. This paper presents Deep Lake, an open-source lakehouse for deep learning applications developed at Activeloop. Deep Lake maintains the benefits of a vanilla data lake with one key difference: it stores complex data, such as images, videos, annotations, as well as tabular data, in the form of tensors and rapidly streams the data over the network to (a) Tensor Query Language, (b) in-browser visualization engine, or (c) deep learning frameworks without sacrificing GPU utilization. Datasets stored in Deep Lake can be accessed from PyTorch, TensorFlow, JAX, and integrate with numerous MLOps tools.

arXiv:2209.10587공식 코드 · Papers with Code

DeepVARwT: Deep Learning for a VAR Model with Trend

The vector autoregressive (VAR) model has been used to describe the dependence within and across multiple time series. This is a model for stationary time series which can be extended to allow the presence of a deterministic trend in each series. Detrending the data either parametrically or nonparametrically before fitting the VAR model gives rise to more errors in the latter part. In this study, we propose a new approach called DeepVARwT that employs deep learning methodology for maximum likelihood estimation of the trend and the dependence structure at the same time. A Long Short-Term Memory (LSTM) network is used for this purpose. To ensure the stability of the model, we enforce the causality condition on the autoregressive coefficients using the transformation of Ansley & Kohn (1986). We provide a simulation study and an application to real data. In the simulation study, we use realistic trend functions generated from real data and compare the estimates with true function/parameter values. In the real data application, we compare the prediction performance of this model with state-of-the-art models in the literature.

arXiv:2209.08411공식 코드 · Papers with Code

DynaConF: Dynamic Forecasting of Non-Stationary Time Series

Deep learning has shown impressive results in a variety of time series forecasting tasks, where modeling the conditional distribution of the future given the past is the essence. However, when this conditional distribution is non-stationary, it poses challenges for these models to learn consistently and to predict accurately. In this work, we propose a new method to model non-stationary conditional distributions over time by clearly decoupling stationary conditional distribution modeling from non-stationary dynamics modeling. Our method is based on a Bayesian dynamic model that can adapt to conditional distribution changes and a deep conditional distribution model that handles multivariate time series using a factorized output space. Our experimental results on synthetic and real-world datasets show that our model can adapt to non-stationary time series better than state-of-the-art deep learning solutions.

arXiv:2209.07805공식 코드 · Papers with Code

A Comprehensive Benchmark for COVID-19 Predictive Modeling Using Electronic Health Records in Intensive Care

The COVID-19 pandemic has posed a heavy burden to the healthcare system worldwide and caused huge social disruption and economic loss. Many deep learning models have been proposed to conduct clinical predictive tasks such as mortality prediction for COVID-19 patients in intensive care units using Electronic Health Record (EHR) data. Despite their initial success in certain clinical applications, there is currently a lack of benchmarking results to achieve a fair comparison so that we can select the optimal model for clinical use. Furthermore, there is a discrepancy between the formulation of traditional prediction tasks and real-world clinical practice in intensive care. To fill these gaps, we propose two clinical prediction tasks, Outcome-specific length-of-stay prediction and Early mortality prediction for COVID-19 patients in intensive care units. The two tasks are adapted from the naive length-of-stay and mortality prediction tasks to accommodate the clinical practice for COVID-19 patients. We propose fair, detailed, open-source data-preprocessing pipelines and evaluate 17 state-of-the-art predictive models on two tasks, including 5 machine learning models, 6 basic deep learning models and 6 deep learning predictive models specifically designed for EHR data. We provide benchmarking results using data from two real-world COVID-19 EHR datasets. One dataset is publicly available without needing any inquiry and another dataset can be accessed on request. We provide fair, reproducible benchmarking results for two tasks. We deploy all experiment results and models on an online platform. We also allow clinicians and researchers to upload their data to the platform and get quick prediction results using our trained models. We hope our efforts can further facilitate deep learning and machine learning research for COVID-19 predictive modeling.

arXiv:2209.07121공식 코드 · Papers with Code

4DenoiseNet: Adverse Weather Denoising from Adjacent Point Clouds

Reliable point cloud data is essential for perception tasks \textit{e.g.} in robotics and autonomous driving applications. Adverse weather causes a specific type of noise to light detection and ranging (LiDAR) sensor data, which degrades the quality of the point clouds significantly. To address this issue, this letter presents a novel point cloud adverse weather denoising deep learning algorithm (4DenoiseNet). Our algorithm takes advantage of the time dimension unlike deep learning adverse weather denoising methods in the literature. It performs about 10\% better in terms of intersection over union metric compared to the previous work and is more computationally efficient. These results are achieved on our novel SnowyKITTI dataset, which has over 40000 adverse weather annotated point clouds. Moreover, strong qualitative results on the Canadian Adverse Driving Conditions dataset indicate good generalizability to domain shifts and to different sensor intrinsics.