PyTorchKR Papers

최신 논문

총 2,063편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1812.07965공식 코드 · Papers with Code

Deep learning with asymmetric connections and Hebbian updates

We show that deep networks can be trained using Hebbian updates yielding similar performance to ordinary back-propagation on challenging image datasets. To overcome the unrealistic symmetry in connections between layers, implicit in back-propagation, the feedback weights are separate from the feedforward weights. The feedback weights are also updated with a local rule, the same as the feedforward weights - a weight is updated solely based on the product of activity of the units it connects. With fixed feedback weights as proposed in Lillicrap et. al (2016) performance degrades quickly as the depth of the network increases. If the feedforward and feedback weights are initialized with the same values, as proposed in Zipser and Rumelhart (1990), they remain the same throughout training thus precisely implementing back-propagation. We show that even when the weights are initialized differently and at random, and the algorithm is no longer performing back-propagation, performance is comparable on challenging datasets. We also propose a cost function whose derivative can be represented as a local Hebbian update on the last layer. Convolutional layers are updated with tied weights across space, which is not biologically plausible. We show that similar performance is achieved with untied layers, also known as locally connected layers, corresponding to the connectivity implied by the convolutional layers, but where weights are untied and updated separately. In the linear case we show theoretically that the convergence of the error to zero is accelerated by the update of the feedback weights.

arXiv:1903.03040공식 코드 · Papers with Code

Deep learning observables in computational fluid dynamics

Many large scale problems in computational fluid dynamics such as uncertainty quantification, Bayesian inversion, data assimilation and PDE constrained optimization are considered very challenging computationally as they require a large number of expensive (forward) numerical solutions of the corresponding PDEs. We propose a machine learning algorithm, based on deep artificial neural networks, that predicts the underlying \emph{input parameters to observable} map from a few training samples (computed realizations of this map). By a judicious combination of theoretical arguments and empirical observations, we find suitable network architectures and training hyperparameters that result in robust and efficient neural network approximations of the parameters to observable map. Numerical experiments are presented to demonstrate low prediction errors for the trained network networks, even when the network has been trained with a few samples, at a computational cost which is several orders of magnitude lower than the underlying PDE solver. Moreover, we combine the proposed deep learning algorithm with Monte Carlo (MC) and Quasi-Monte Carlo (QMC) methods to efficiently compute uncertainty propagation for nonlinear PDEs. Under the assumption that the underlying neural networks generalize well, we prove that the deep learning MC and QMC algorithms are guaranteed to be faster than the baseline (quasi-) Monte Carlo methods. Numerical experiments demonstrating one to two orders of magnitude speed up over baseline QMC and MC algorithms, for the intricate problem of computing probability distributions of the observable, are also presented.

arXiv:1903.02788공식 코드 · Papers with Code

Interpretable Deep Learning in Drug Discovery

Without any means of interpretation, neural networks that predict molecular properties and bioactivities are merely black boxes. We will unravel these black boxes and will demonstrate approaches to understand the learned representations which are hidden inside these models. We show how single neurons can be interpreted as classifiers which determine the presence or absence of pharmacophore- or toxicophore-like structures, thereby generating new insights and relevant knowledge for chemistry, pharmacology and biochemistry. We further discuss how these novel pharmacophores/toxicophores can be determined from the network by identifying the most relevant components of a compound for the prediction of the network. Additionally, we propose a method which can be used to extract new pharmacophores from a model and will show that these extracted structures are consistent with literature findings. We envision that having access to such interpretable knowledge is a crucial aid in the development and design of new pharmaceutically active molecules, and helps to investigate and understand failures and successes of current methods.

arXiv:1903.02063공식 코드 · Papers with Code

PatchNet: A Tool for Deep Patch Classification

This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the hierarchical and sequential structure of a code change, differentiating it from the existing deep learning models on source code. PatchNet provides several options allowing users to select parameters for the training process. The tool has been validated in the context of automatic identification of stable-relevant patches in the Linux kernel and is potentially applicable to automate other software engineering tasks that can be formulated as patch classification problems. A video demonstrating PatchNet is available at https://goo.gl/CZjG6X. The PatchNet implementation is available at https://github.com/hvdthong/PatchNetTool.

arXiv:1903.00342공식 코드 · Papers with Code

Deep learning in bioinformatics: introduction, application, and perspective in big data era

Deep learning, which is especially formidable in handling big data, has achieved great success in various fields, including bioinformatics. With the advances of the big data era in biology, it is foreseeable that deep learning will become increasingly important in the field and will be incorporated in vast majorities of analysis pipelines. In this review, we provide both the exoteric introduction of deep learning, and concrete examples and implementations of its representative applications in bioinformatics. We start from the recent achievements of deep learning in the bioinformatics field, pointing out the problems which are suitable to use deep learning. After that, we introduce deep learning in an easy-to-understand fashion, from shallow neural networks to legendary convolutional neural networks, legendary recurrent neural networks, graph neural networks, generative adversarial networks, variational autoencoder, and the most recent state-of-the-art architectures. After that, we provide eight examples, covering five bioinformatics research directions and all the four kinds of data type, with the implementation written in Tensorflow and Keras. Finally, we discuss the common issues, such as overfitting and interpretability, that users will encounter when adopting deep learning methods and provide corresponding suggestions. The implementations are freely available at \url{https://github.com/lykaust15/Deep_learning_examples}.

arXiv:1902.10644공식 코드 · Papers with Code

Provable Guarantees for Gradient-Based Meta-Learning

We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods. Our method is the first to simultaneously satisfy good sample efficiency guarantees in the convex setting, with generalization bounds that improve with task-similarity, while also being computationally scalable to modern deep learning architectures and the many-task setting. Despite its simplicity, the algorithm matches, up to a constant factor, a lower bound on the performance of any such parameter-transfer method under natural task similarity assumptions. We use experiments in both convex and deep learning settings to verify and demonstrate the applicability of our theory.

arXiv:1902.08788공식 코드 · Papers with Code

Facial Motion Prior Networks for Facial Expression Recognition

Deep learning based facial expression recognition (FER) has received a lot of attention in the past few years. Most of the existing deep learning based FER methods do not consider domain knowledge well, which thereby fail to extract representative features. In this work, we propose a novel FER framework, named Facial Motion Prior Networks (FMPN). Particularly, we introduce an addition branch to generate a facial mask so as to focus on facial muscle moving regions. To guide the facial mask learning, we propose to incorporate prior domain knowledge by using the average differences between neutral faces and the corresponding expressive faces as the training guidance. Extensive experiments on three facial expression benchmark datasets demonstrate the effectiveness of the proposed method, compared with the state-of-the-art approaches.

arXiv:1902.06714공식 코드 · Papers with Code

A parallel Fortran framework for neural networks and deep learning

This paper describes neural-fortran, a parallel Fortran framework for neural networks and deep learning. It features a simple interface to construct feed-forward neural networks of arbitrary structure and size, several activation functions, and stochastic gradient descent as the default optimization algorithm. Neural-fortran also leverages the Fortran 2018 standard collective subroutines to achieve data-based parallelism on shared- or distributed-memory machines. First, I describe the implementation of neural networks with Fortran derived types, whole-array arithmetic, and collective sum and broadcast operations to achieve parallelism. Second, I demonstrate the use of neural-fortran in an example of recognizing hand-written digits from images. Finally, I evaluate the computational performance in both serial and parallel modes. Ease of use and computational performance are similar to an existing popular machine learning framework, making neural-fortran a viable candidate for further development and use in production.

arXiv:1902.06068공식 코드 · Papers with Code

Deep Learning for Image Super-resolution: A Survey

Image Super-Resolution (SR) is an important class of image processing techniques to enhance the resolution of images and videos in computer vision. Recent years have witnessed remarkable progress of image super-resolution using deep learning techniques. This article aims to provide a comprehensive survey on recent advances of image super-resolution using deep learning approaches. In general, we can roughly group the existing studies of SR techniques into three major categories: supervised SR, unsupervised SR, and domain-specific SR. In addition, we also cover some other important issues, such as publicly available benchmark datasets and performance evaluation metrics. Finally, we conclude this survey by highlighting several future directions and open issues which should be further addressed by the community in the future.

arXiv:1902.05300공식 코드 · Papers with Code

On instabilities of deep learning in image reconstruction - Does AI come at a cost?

Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper we demonstrate a crucial phenomenon: deep learning typically yields unstablemethods for image reconstruction. The instabilities usually occur in several forms: (1) tiny, almost undetectable perturbations, both in the image and sampling domain, may result in severe artefacts in the reconstruction, (2) a small structural change, for example a tumour, may not be captured in the reconstructed image and (3) (a counterintuitive type of instability) more samples may yield poorer performance. Our new stability test with algorithms and easy to use software detects the instability phenomena. The test is aimed at researchers to test their networks for instabilities and for government agencies, such as the Food and Drug Administration (FDA), to secure safe use of deep learning methods.

arXiv:1902.04742공식 코드 · Papers with Code

Uniform convergence may be unable to explain generalization in deep learning

Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic technique of uniform convergence. While it is well-known that many of these existing bounds are numerically large, through numerous experiments, we bring to light a more concerning aspect of these bounds: in practice, these bounds can {\em increase} with the training dataset size. Guided by our observations, we then present examples of overparameterized linear classifiers and neural networks trained by gradient descent (GD) where uniform convergence provably cannot "explain generalization" -- even if we take into account the implicit bias of GD {\em to the fullest extent possible}. More precisely, even if we consider only the set of classifiers output by GD, which have test errors less than some small $\epsilon$ in our settings, we show that applying (two-sided) uniform convergence on this set of classifiers will yield only a vacuous generalization guarantee larger than $1-\epsilon$. Through these findings, we cast doubt on the power of uniform convergence-based generalization bounds to provide a complete picture of why overparameterized deep networks generalize well.

arXiv:1902.04610공식 코드 · Papers with Code

Salus: Fine-Grained GPU Sharing Primitives for Deep Learning Applications

GPU computing is becoming increasingly more popular with the proliferation of deep learning (DL) applications. However, unlike traditional resources such as CPU or the network, modern GPUs do not natively support fine-grained sharing primitives. Consequently, implementing common policies such as time sharing and preemption are expensive. Worse, when a DL application cannot completely use a GPU's resources, the GPU cannot be efficiently shared between multiple applications, leading to GPU underutilization. We present Salus to enable two GPU sharing primitives: fast job switching and memory sharing, in order to achieve fine-grained GPU sharing among multiple DL applications. Salus implements an efficient, consolidated execution service that exposes the GPU to different DL applications, and enforces fine-grained sharing by performing iteration scheduling and addressing associated memory management issues. We show that these primitives can then be used to implement flexible sharing policies such as fairness, prioritization, and packing for various use cases. Our integration of Salus with TensorFlow and evaluation on popular DL jobs show that Salus can improve the average completion time of DL training jobs by $3.19\times$, GPU utilization for hyper-parameter tuning by $2.38\times$, and GPU utilization of DL inference applications by $42\times$ over not sharing the GPU and $7\times$ over NVIDIA MPS with small overhead.

arXiv:1902.04166공식 코드 · Papers with Code

WideDTA: prediction of drug-target binding affinity

Motivation: Prediction of the interaction affinity between proteins and compounds is a major challenge in the drug discovery process. WideDTA is a deep-learning based prediction model that employs chemical and biological textual sequence information to predict binding affinity. Results: WideDTA uses four text-based information sources, namely the protein sequence, ligand SMILES, protein domains and motifs, and maximum common substructure words to predict binding affinity. WideDTA outperformed one of the state of the art deep learning methods for drug-target binding affinity prediction, DeepDTA on the KIBA dataset with a statistical significance. This indicates that the word-based sequence representation adapted by WideDTA is a promising alternative to the character-based sequence representation approach in deep learning models for binding affinity prediction, such as the one used in DeepDTA. In addition, the results showed that, given the protein sequence and ligand SMILES, the inclusion of protein domain and motif information as well as ligand maximum common substructure words do not provide additional useful information for the deep learning model. Interestingly, however, using only domain and motif information to represent proteins achieved similar performance to using the full protein sequence, suggesting that important binding relevant information is contained within the protein motifs and domains.

arXiv:1902.03932공식 코드 · Papers with Code

Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning

The posteriors over neural network weights are high dimensional and multimodal. Each mode typically characterizes a meaningfully different representation of the data. We develop Cyclical Stochastic Gradient MCMC (SG-MCMC) to automatically explore such distributions. In particular, we propose a cyclical stepsize schedule, where larger steps discover new modes, and smaller steps characterize each mode. We also prove non-asymptotic convergence of our proposed algorithm. Moreover, we provide extensive experimental results, including ImageNet, to demonstrate the scalability and effectiveness of cyclical SG-MCMC in learning complex multimodal distributions, especially for fully Bayesian inference with modern deep neural networks.

arXiv:1902.02476공식 코드 · Papers with Code

A Simple Baseline for Bayesian Uncertainty in Deep Learning

We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA), which computes the first moment of stochastic gradient descent (SGD) iterates with a modified learning rate schedule, has recently been shown to improve generalization in deep learning. With SWAG, we fit a Gaussian using the SWA solution as the first moment and a low rank plus diagonal covariance also derived from the SGD iterates, forming an approximate posterior distribution over neural network weights; we then sample from this Gaussian distribution to perform Bayesian model averaging. We empirically find that SWAG approximates the shape of the true posterior, in accordance with results describing the stationary distribution of SGD iterates. Moreover, we demonstrate that SWAG performs well on a wide variety of tasks, including out of sample detection, calibration, and transfer learning, in comparison to many popular alternatives including MC dropout, KFAC Laplace, SGLD, and temperature scaling.

arXiv:1902.02060공식 코드 · Papers with Code

On ADMM in Deep Learning: Convergence and Saturation-Avoidance

In this paper, we develop an alternating direction method of multipliers (ADMM) for deep neural networks training with sigmoid-type activation functions (called \textit{sigmoid-ADMM pair}), mainly motivated by the gradient-free nature of ADMM in avoiding the saturation of sigmoid-type activations and the advantages of deep neural networks with sigmoid-type activations (called deep sigmoid nets) over their rectified linear unit (ReLU) counterparts (called deep ReLU nets) in terms of approximation. In particular, we prove that the approximation capability of deep sigmoid nets is not worse than that of deep ReLU nets by showing that ReLU activation function can be well approximated by deep sigmoid nets with two hidden layers and finitely many free parameters but not vice-verse. We also establish the global convergence of the proposed ADMM for the nonlinearly constrained formulation of the deep sigmoid nets training from arbitrary initial points to a Karush-Kuhn-Tucker (KKT) point at a rate of order ${\cal O}(1/k)$. Besides sigmoid activation, such a convergence theorem holds for a general class of smooth activations. Compared with the widely used stochastic gradient descent (SGD) algorithm for the deep ReLU nets training (called ReLU-SGD pair), the proposed sigmoid-ADMM pair is practically stable with respect to the algorithmic hyperparameters including the learning rate, initial schemes and the pro-processing of the input data. Moreover, we find that to approximate and learn simple but important functions the proposed sigmoid-ADMM pair numerically outperforms the ReLU-SGD pair.

arXiv:1902.01659공식 코드 · Papers with Code

Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping

Sepsis is a life-threatening host response to infection associated with high mortality, morbidity, and health costs. Its management is highly time-sensitive since each hour of delayed treatment increases mortality due to irreversible organ damage. Meanwhile, despite decades of clinical research, robust biomarkers for sepsis are missing. Therefore, detecting sepsis early by utilizing the affluence of high-resolution intensive care records has become a challenging machine learning problem. Recent advances in deep learning and data mining promise to deliver a powerful set of tools to efficiently address this task. This empirical study proposes two novel approaches for the early detection of sepsis: a deep learning model and a lazy learner based on time series distances. Our deep learning model employs a temporal convolutional network that is embedded in a Multi-task Gaussian Process Adapter framework, making it directly applicable to irregularly-spaced time series data. Our lazy learner, by contrast, is an ensemble approach that employs dynamic time warping. We frame the timely detection of sepsis as a supervised time series classification task. For this, we derive the most recent sepsis definition in an hourly resolution to provide the first fully accessible early sepsis detection environment. Seven hours before sepsis onset, our methods improve area under the precision--recall curve from 0.25 to 0.35/0.40 over the state of the art. This demonstrates that they are well-suited for detecting sepsis in the crucial earlier stages when management is most effective.

arXiv:1902.00407공식 코드 · Papers with Code

Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation

Current methods to interpret deep learning models by generating saliency maps generally rely on two key assumptions. First, they use first-order approximations of the loss function neglecting higher-order terms such as the loss curvatures. Second, they evaluate each feature's importance in isolation, ignoring their inter-dependencies. In this work, we study the effect of relaxing these two assumptions. First, by characterizing a closed-form formula for the Hessian matrix of a deep ReLU network, we prove that, for a classification problem with a large number of classes, if an input has a high confidence classification score, the inclusion of the Hessian term has small impacts in the final solution. We prove this result by showing that in this case the Hessian matrix is approximately of rank one and its leading eigenvector is almost parallel to the gradient of the loss function. Our empirical experiments on ImageNet samples are consistent with our theory. This result can have implications in other related problems such as adversarial examples as well. Second, we compute the importance of group-features in deep learning interpretation by introducing a sparsity regularization term. We use the $L_0-L_1$ relaxation technique along with the proximal gradient descent to have an efficient computation of group feature importance scores. Our empirical results indicate that considering group features can improve deep learning interpretation significantly.

arXiv:1901.11210공식 코드 · Papers with Code

Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System

In order to bridge the gap between Deep Learning researchers and medical professionals we develop a very accessible free prototype system which can be used by medical professionals to understand the reality of Deep Learning tools for chest X-ray diagnostics. The system is designed to be a second opinion where a user can process an image to confirm or aid in their diagnosis. Code and network weights are delivered via a URL to a web browser (including cell phones) but the patient data remains on the users machine and all processing occurs locally. This paper discusses the three main components in detail: out-of-distribution detection, disease prediction, and prediction explanation. The system open source and freely available here: https://mlmed.org/tools/xray

arXiv:1901.10826공식 코드 · Papers with Code

Additive Margin SincNet for Speaker Recognition

Speaker Recognition is a challenging task with essential applications such as authentication, automation, and security. The SincNet is a new deep learning based model which has produced promising results to tackle the mentioned task. To train deep learning systems, the loss function is essential to the network performance. The Softmax loss function is a widely used function in deep learning methods, but it is not the best choice for all kind of problems. For distance-based problems, one new Softmax based loss function called Additive Margin Softmax (AM-Softmax) is proving to be a better choice than the traditional Softmax. The AM-Softmax introduces a margin of separation between the classes that forces the samples from the same class to be closer to each other and also maximizes the distance between classes. In this paper, we propose a new approach for speaker recognition systems called AM-SincNet, which is based on the SincNet but uses an improved AM-Softmax layer. The proposed method is evaluated in the TIMIT dataset and obtained an improvement of approximately 40% in the Frame Error Rate compared to SincNet.