PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2104.04132

Replay in Deep Learning: Current Approaches and Missing Biological Elements

Replay is the reactivation of one or more neural patterns, which are similar to the activation patterns experienced during past waking experiences. Replay was first observed in biological neural networks during sleep, and it is now thought to play a critical role in memory formation, retrieval, and consolidation. Replay-like mechanisms have been incorporated into deep artificial neural networks that learn over time to avoid catastrophic forgetting of previous knowledge. Replay algorithms have been successfully used in a wide range of deep learning methods within supervised, unsupervised, and reinforcement learning paradigms. In this paper, we provide the first comprehensive comparison between replay in the mammalian brain and replay in artificial neural networks. We identify multiple aspects of biological replay that are missing in deep learning systems and hypothesize how they could be utilized to improve artificial neural networks.

arXiv:2104.04485

A Data-Driven Approach to Full-Field Damage and Failure Pattern Prediction in Microstructure-Dependent Composites using Deep Learning

An image-based deep learning framework is developed in this paper to predict damage and failure in microstructure-dependent composite materials. The work is motivated by the complexity and computational cost of high-fidelity simulations of such materials. The proposed deep learning framework predicts the post-failure full-field stress distribution and crack pattern in two-dimensional representations of the composites based on the geometry of microstructures. The material of interest is selected to be a high-performance unidirectional carbon fiber-reinforced polymer composite. The deep learning framework contains two stacked fully-convolutional networks, namely, Generator 1 and Generator 2, trained sequentially. First, Generator 1 learns to translate the microstructural geometry to the full-field post-failure stress distribution. Then, Generator 2 learns to translate the output of Generator 1 to the failure pattern. A physics-informed loss function is also designed and incorporated to further improve the performance of the proposed framework and facilitate the validation process. In order to provide a sufficiently large data set for training and validating the deep learning framework, 4500 microstructural representations are synthetically generated and simulated in an efficient finite element framework. It is shown that the proposed deep learning approach can effectively predict the composites' post-failure full-field stress distribution and failure pattern, two of the most complex phenomena to simulate in computational solid mechanics.

arXiv:2104.04377

Blending Knowledge in Deep Recurrent Networks for Adverse Event Prediction at Hospital Discharge

Deep learning architectures have an extremely high-capacity for modeling complex data in a wide variety of domains. However, these architectures have been limited in their ability to support complex prediction problems using insurance claims data, such as readmission at 30 days, mainly due to data sparsity issue. Consequently, classical machine learning methods, especially those that embed domain knowledge in handcrafted features, are often on par with, and sometimes outperform, deep learning approaches. In this paper, we illustrate how the potential of deep learning can be achieved by blending domain knowledge within deep learning architectures to predict adverse events at hospital discharge, including readmissions. More specifically, we introduce a learning architecture that fuses a representation of patient data computed by a self-attention based recurrent neural network, with clinically relevant features. We conduct extensive experiments on a large claims dataset and show that the blended method outperforms the standard machine learning approaches.

arXiv:2104.03494

A Deep Ensemble-based Wireless Receiver Architecture for Mitigating Adversarial Attacks in Automatic Modulation Classification

Deep learning-based automatic modulation classification (AMC) models are susceptible to adversarial attacks. Such attacks inject specifically crafted wireless interference into transmitted signals to induce erroneous classification predictions. Furthermore, adversarial interference is transferable in black box environments, allowing an adversary to attack multiple deep learning models with a single perturbation crafted for a particular classification model. In this work, we propose a novel wireless receiver architecture to mitigate the effects of adversarial interference in various black box attack environments. We begin by evaluating the architecture uncertainty environment, where we show that adversarial attacks crafted to fool specific AMC DL architectures are not directly transferable to different DL architectures. Next, we consider the domain uncertainty environment, where we show that adversarial attacks crafted on time domain and frequency domain features to not directly transfer to the altering domain. Using these insights, we develop our Assorted Deep Ensemble (ADE) defense, which is an ensemble of deep learning architectures trained on time and frequency domain representations of received signals. Through evaluation on two wireless signal datasets under different sources of uncertainty, we demonstrate that our ADE obtains substantial improvements in AMC classification performance compared with baseline defenses across different adversarial attacks and potencies.

논문 ID: document/9386067

Building a Scalable and Interpretable Bayesian Deep Learning Framework for Quality Control of Free Form Surfaces

Deep learning has demonstrated high accuracy for 3D object shape error modeling necessary to estimate dimensional and geometric quality defects in multi-station assembly systems (MAS). Increasingly, deep learning-driven Root Cause Analysis (RCA) is used for decision-making when planning corrective action of quality defects. However, given the current absence of scalability enabling models, training deep learning models for each individual MAS is exceedingly time-consuming as it requires large amounts of labelled data and multiple computational cycles. Additionally, understanding and interpreting how deep learning produces final predictions while quantifying various uncertainties also remains a fundamental challenge. In an effort to address these gaps, a novel closed-loop in-process (CLIP) diagnostic framework underpinned algorithm portfolio is proposed which simultaneously enhances scalability and interpretability of the current Bayesian deep learning approach, Object Shape Error Response (OSER), to isolate root cause(s) of quality defects in MAS. The OSER-MAS leverages a Bayesian 3D U-Net architecture integrated with Computer-Aided Engineering simulations to estimate root causes. The CLIP diagnostic framework shortens OSER-MAS model training time by developing: (i) closed-loop training to enable faster convergence for a single MAS by leveraging uncertainty estimates of the Bayesian 3D U-net model; and, (ii) transfer/continual learning-based scalability model to transmit meta-knowledge from the trained model to a new MAS resulting in convergence using comparatively less training samples. Additionally, CLIP increases the transparency for quality-related root cause predictions by developing interpretability model which is based on 3D Gradient-based Class Activation Maps (3D Grad-CAMs) and entails: (a) linking elements of MAS model with functional elements of the U-Net architecture; and, (b) relating features extracted by the architecture with elements of the MAS model and further with the object shape error patterns for root cause(s) that occur in MAS. Benchmarking studies are conducted using six automotive-MAS with varying complexities. Results highlight a reduction in training samples of up to 56% with a loss in performance of up to 2.1%.

arXiv:2104.03804

Exact Stochastic Second Order Deep Learning

Optimization in Deep Learning is mainly dominated by first-order methods which are built around the central concept of backpropagation. Second-order optimization methods, which take into account the second-order derivatives are far less used despite superior theoretical properties. This inadequacy of second-order methods stems from its exorbitant computational cost, poor performance, and the ineluctable non-convex nature of Deep Learning. Several attempts were made to resolve the inadequacy of second-order optimization without reaching a cost-effective solution, much less an exact solution. In this work, we show that this long-standing problem in Deep Learning could be solved in the stochastic case, given a suitable regularization of the neural network. Interestingly, we provide an expression of the stochastic Hessian and its exact eigenvalues. We provide a closed-form formula for the exact stochastic second-order Newton direction, we solve the non-convexity issue and adjust our exact solution to favor flat minima through regularization and spectral adjustment. We test our exact stochastic second-order method on popular datasets and reveal its adequacy for Deep Learning.

arXiv:2104.03739

CARRNN: A Continuous Autoregressive Recurrent Neural Network for Deep Representation Learning from Sporadic Temporal Data

Learning temporal patterns from multivariate longitudinal data is challenging especially in cases when data is sporadic, as often seen in, e.g., healthcare applications where the data can suffer from irregularity and asynchronicity as the time between consecutive data points can vary across features and samples, hindering the application of existing deep learning models that are constructed for complete, evenly spaced data with fixed sequence lengths. In this paper, a novel deep learning-based model is developed for modeling multiple temporal features in sporadic data using an integrated deep learning architecture based on a recurrent neural network (RNN) unit and a continuous-time autoregressive (CAR) model. The proposed model, called CARRNN, uses a generalized discrete-time autoregressive model that is trainable end-to-end using neural networks modulated by time lags to describe the changes caused by the irregularity and asynchronicity. It is applied to multivariate time-series regression tasks using data provided for Alzheimer's disease progression modeling and intensive care unit (ICU) mortality rate prediction, where the proposed model based on a gated recurrent unit (GRU) achieves the lowest prediction errors among the proposed RNN-based models and state-of-the-art methods using GRUs and long short-term memory (LSTM) networks in their architecture.

arXiv:2104.03624

Post-Hoc Domain Adaptation via Guided Data Homogenization

Addressing shifts in data distributions is an important prerequisite for the deployment of deep learning models to real-world settings. A general approach to this problem involves the adjustment of models to a new domain through transfer learning. However, in many cases, this is not applicable in a post-hoc manner to deployed models and further parameter adjustments jeopardize safety certifications that were established beforehand. In such a context, we propose to deal with changes in the data distribution via guided data homogenization which shifts the burden of adaptation from the model to the data. This approach makes use of information about the training data contained implicitly in the deep learning model to learn a domain transfer function. This allows for a targeted deployment of models to unknown scenarios without changing the model itself. We demonstrate the potential of data homogenization through experiments on the CIFAR-10 and MNIST data sets.

arXiv:2104.02746

Proof of the Theory-to-Practice Gap in Deep Learning via Sampling Complexity bounds for Neural Network Approximation Spaces

We study the computational complexity of (deterministic or randomized) algorithms based on point samples for approximating or integrating functions that can be well approximated by neural networks. Such algorithms (most prominently stochastic gradient descent and its variants) are used extensively in the field of deep learning. One of the most important problems in this field concerns the question of whether it is possible to realize theoretically provable neural network approximation rates by such algorithms. We answer this question in the negative by proving hardness results for the problems of approximation and integration on a novel class of neural network approximation spaces. In particular, our results confirm a conjectured and empirically observed theory-to-practice gap in deep learning. We complement our hardness results by showing that approximation rates of a comparable order of convergence are (at least theoretically) achievable.

arXiv:2104.03226

Evaluation of Time Series Forecasting Models for Estimation of PM2.5 Levels in Air

Air contamination in urban areas has risen consistently over the past few years. Due to expanding industrialization and increasing concentration of toxic gases in the climate, the air is getting more poisonous step by step at an alarming rate. Since the arrival of the Coronavirus pandemic, it is getting more critical to lessen air contamination to reduce its impact. The specialists and environmentalists are making a valiant effort to gauge air contamination levels. However, its genuinely unpredictable to mimic subatomic communication in the air, which brings about off base outcomes. There has been an ascent in using machine learning and deep learning models to foresee the results on time series data. This study adopts ARIMA, FBProphet, and deep learning models such as LSTM, 1D CNN, to estimate the concentration of PM2.5 in the environment. Our predicted results convey that all adopted methods give comparative outcomes in terms of average root mean squared error. However, the LSTM outperforms all other models with reference to mean absolute percentage error.

arXiv:2104.03130

Dense Dilated UNet: Deep Learning for 3D Photoacoustic Tomography Image Reconstruction

In photoacoustic tomography (PAT), the acoustic pressure waves produced by optical excitation are measured by an array of detectors and used to reconstruct an image. Sparse spatial sampling and limited-view detection are two common challenges faced in PAT. Reconstructing from incomplete data using standard methods results in severe streaking artifacts and blurring. We propose a modified convolutional neural network (CNN) architecture termed Dense Dilation UNet (DD-UNet) for correcting artifacts in 3D PAT. The DD-Net leverages the benefits of dense connectivity and dilated convolutions to improve CNN performance. We compare the proposed CNN in terms of image quality as measured by the multiscale structural similarity index metric to the Fully Dense UNet (FD-UNet). Results demonstrate that the DD-Net consistently outperforms the FD-UNet and is able to more reliably reconstruct smaller image features.

arXiv:2104.02980

Synthetic training data generation for deep learning based quality inspection

Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly: collecting, cleaning, and annotating the data is tedious and limits the speed at which a system can be deployed as everything the system must detect needs to be observed first. This can impede the inspection of rare defects, since very few samples can be collected by the manufacturer. In this work, we focus on simulations to solve this issue. We first present a generic simulation pipeline to render images of defective or healthy (non defective) parts. As metallic parts can be highly textured with small defects like holes, we design a texture scanning and generation method. We assess the quality of the generated images by training deep learning networks and by testing them on real data from a manufacturer. We demonstrate that we can achieve encouraging results on real defect detection using purely simulated data. Additionally, we are able to improve global performances by concatenating simulated and real data, showing that simulations can complement real images to boost performances. Lastly, using domain adaptation techniques helps improving slightly our final results.

arXiv:2104.02655

DeepBlur: A Simple and Effective Method for Natural Image Obfuscation

There is a growing privacy concern due to the popularity of social media and surveillance systems, along with advances in face recognition software. However, established image obfuscation techniques are either vulnerable to re-identification attacks by human or deep learning models, insufficient in preserving image fidelity, or too computationally intensive to be practical. To tackle these issues, we present DeepBlur, a simple yet effective method for image obfuscation by blurring in the latent space of an unconditionally pre-trained generative model that is able to synthesize photo-realistic facial images. We compare it with existing methods by efficiency and image quality, and evaluate against both state-of-the-art deep learning models and industrial products (e.g., Face++, Microsoft face service). Experiments show that our method produces high quality outputs and is the strongest defense for most test cases.

arXiv:2104.02550

Deep learning for prediction of complex geology ahead of drilling

During a geosteering operation the well path is intentionally adjusted in response to the new data acquired while drilling. To achieve consistent high-quality decisions, especially when drilling in complex environments, decision support systems can help cope with high volumes of data and interpretation complexities. They can assimilate the real-time measurements into a probabilistic earth model and use the updated model for decision recommendations. Recently, machine learning (ML) techniques have enabled a wide range of methods that redistribute computational cost from on-line to off-line calculations. In this paper, we introduce two ML techniques into the geosteering decision support framework. Firstly, a complex earth model representation is generated using a Generative Adversarial Network (GAN). Secondly, a commercial extra-deep electromagnetic simulator is represented using a Forward Deep Neural Network (FDNN). The numerical experiments demonstrate that the combination of the GAN and the FDNN in an ensemble randomized maximum likelihood data assimilation scheme provides real-time estimates of complex geological uncertainty. This yields reduction of geological uncertainty ahead of the drill-bit from the measurements gathered behind and around the well bore.

arXiv:2104.02278

A novel activity pattern generation incorporating deep learning for transport demand models

Activity generation plays an important role in activity-based demand modelling systems. While machine learning, especially deep learning, has been increasingly used for mode choice and traffic flow prediction, much less research exploiting the advantage of deep learning for activity generation tasks. This paper proposes a novel activity pattern generation framework by incorporating deep learning with travel domain knowledge. We model each activity schedule as one primary activity tour and several secondary activity tours. We then develop different deep neural networks with entity embedding and random forest models to classify activity type, as well as to predict activity times. The proposed framework can capture the activity patterns for individuals in both training and validation sets. Results show high accuracy for the start time and end time of work and school activities. The framework also replicates the start time patterns of stop-before and stop-after primary work activity well. This provides a promising direction to deploy advanced machine learning methods to generate more reliable activity-travel patterns for transport demand systems and their applications.

arXiv:2104.02102공식 코드 · Papers with Code

Automated Performance Testing Based on Active Deep Learning

Generating tests that can reveal performance issues in large and complex software systems within a reasonable amount of time is a challenging task. On one hand, there are numerous combinations of input data values to explore. On the other hand, we have a limited test budget to execute tests. What makes this task even more difficult is the lack of access to source code and the internal details of these systems. In this paper, we present an automated test generation method called ACTA for black-box performance testing. ACTA is based on active learning, which means that it does not require a large set of historical test data to learn about the performance characteristics of the system under test. Instead, it dynamically chooses the tests to execute using uncertainty sampling. ACTA relies on a conditional variant of generative adversarial networks,and facilitates specifying performance requirements in terms of conditions and generating tests that address those conditions.We have evaluated ACTA on a benchmark web application, and the experimental results indicate that this method is comparable with random testing, and two other machine learning methods,i.e. PerfXRL and DN.

arXiv:2104.02705

deepregression: a Flexible Neural Network Framework for Semi-Structured Deep Distributional Regression

In this paper we describe the implementation of semi-structured deep distributional regression, a flexible framework to learn conditional distributions based on the combination of additive regression models and deep networks. Our implementation encompasses (1) a modular neural network building system based on the deep learning library \pkg{TensorFlow} for the fusion of various statistical and deep learning approaches, (2) an orthogonalization cell to allow for an interpretable combination of different subnetworks, as well as (3) pre-processing steps necessary to set up such models. The software package allows to define models in a user-friendly manner via a formula interface that is inspired by classical statistical model frameworks such as \pkg{mgcv}. The packages' modular design and functionality provides a unique resource for both scalable estimation of complex statistical models and the combination of approaches from deep learning and statistics. This allows for state-of-the-art predictive performance while simultaneously retaining the indispensable interpretability of classical statistical models.

arXiv:2104.02653

On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study

Deep learning models need large amounts of data for training. In video recognition and classification, significant advances were achieved with the introduction of new large databases. However, the creation of large-databases for training is infeasible in several scenarios. Thus, existing or small collected databases are typically joined and amplified to train these models. Nevertheless, training neural networks on limited data is not straightforward and comes with a set of problems. In this paper, we explore the effects of stacking databases, model initialization, and data amplification techniques when training with limited data on deep learning models' performance. We focused on the problem of Facial Expression Recognition from videos. We performed an extensive study with four databases at a different complexity and nine deep-learning architectures for video classification. We found that (i) complex training sets translate better to more stable test sets when trained with transfer learning and synthetically generated data, but their performance yields a high variance; (ii) training with more detailed data translates to more stable performance on novel scenarios (albeit with lower performance); (iii) merging heterogeneous data is not a straightforward improvement, as the type of augmentation and initialization is crucial; (iv) classical data augmentation cannot fill the holes created by joining largely separated datasets; and (v) inductive biases help to bridge the gap when paired with synthetic data, but this data is not enough when working with standard initialization techniques.

arXiv:2104.02395

Ensemble deep learning: A review

Ensemble learning combines several individual models to obtain better generalization performance. Currently, deep learning architectures are showing better performance compared to the shallow or traditional models. Deep ensemble learning models combine the advantages of both the deep learning models as well as the ensemble learning such that the final model has better generalization performance. This paper reviews the state-of-art deep ensemble models and hence serves as an extensive summary for the researchers. The ensemble models are broadly categorised into bagging, boosting, stacking, negative correlation based deep ensemble models, explicit/implicit ensembles, homogeneous/heterogeneous ensemble, decision fusion strategies based deep ensemble models. Applications of deep ensemble models in different domains are also briefly discussed. Finally, we conclude this paper with some potential future research directions.

arXiv:2104.01874공식 코드 · Papers with Code

Deep Learning of Conjugate Mappings

Despite many of the most common chaotic dynamical systems being continuous in time, it is through discrete time mappings that much of the understanding of chaos is formed. Henri Poincar\'e first made this connection by tracking consecutive iterations of the continuous flow with a lower-dimensional, transverse subspace. The mapping that iterates the dynamics through consecutive intersections of the flow with the subspace is now referred to as a Poincar\'e map, and it is the primary method available for interpreting and classifying chaotic dynamics. Unfortunately, in all but the simplest systems, an explicit form for such a mapping remains outstanding. This work proposes a method for obtaining explicit Poincar\'e mappings by using deep learning to construct an invertible coordinate transformation into a conjugate representation where the dynamics are governed by a relatively simple chaotic mapping. The invertible change of variable is based on an autoencoder, which allows for dimensionality reduction, and has the advantage of classifying chaotic systems using the equivalence relation of topological conjugacies. Indeed, the enforcement of topological conjugacies is the critical neural network regularization for learning the coordinate and dynamics pairing. We provide expository applications of the method to low-dimensional systems such as the R\"ossler and Lorenz systems, while also demonstrating the utility of the method on infinite-dimensional systems, such as the Kuramoto--Sivashinsky equation.