PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1912.07464

Realization of spatial sparseness by deep ReLU nets with massive data

The great success of deep learning poses urgent challenges for understanding its working mechanism and rationality. The depth, structure, and massive size of the data are recognized to be three key ingredients for deep learning. Most of the recent theoretical studies for deep learning focus on the necessity and advantages of depth and structures of neural networks. In this paper, we aim at rigorous verification of the importance of massive data in embodying the out-performance of deep learning. To approximate and learn spatially sparse and smooth functions, we establish a novel sampling theorem in learning theory to show the necessity of massive data. We then prove that implementing the classical empirical risk minimization on some deep nets facilitates in realization of the optimal learning rates derived in the sampling theorem. This perhaps explains why deep learning performs so well in the era of big data.

arXiv:1912.06332공식 코드 · Papers with Code

TopoAct: Visually Exploring the Shape of Activations in Deep Learning

Deep neural networks such as GoogLeNet, ResNet, and BERT have achieved impressive performance in tasks such as image and text classification. To understand how such performance is achieved, we probe a trained deep neural network by studying neuron activations, i.e., combinations of neuron firings, at various layers of the network in response to a particular input. With a large number of inputs, we aim to obtain a global view of what neurons detect by studying their activations. In particular, we develop visualizations that show the shape of the activation space, the organizational principle behind neuron activations, and the relationships of these activations within a layer. Applying tools from topological data analysis, we present TopoAct, a visual exploration system to study topological summaries of activation vectors. We present exploration scenarios using TopoAct that provide valuable insights into learned representations of neural networks. We expect TopoAct to give a topological perspective that enriches the current toolbox of neural network analysis, and to provide a basis for network architecture diagnosis and data anomaly detection.

arXiv:1912.06199

Greenery Segmentation In Urban Images By Deep Learning

Vegetation is a relevant feature in the urban scenery and its awareness can be measured in an image by the Green View Index (GVI). Previous approaches to estimate the GVI were based upon heuristics image processing approaches and recently by deep learning networks (DLN). By leveraging some recent DLN architectures tuned to the image segmentation problem and exploiting a weighting strategy in the loss function (LF) we improved previously reported results in similar datasets.

arXiv:1912.05916공식 코드 · Papers with Code

Deep-Learning Estimation of Band Gap with the Reading-Periodic-Table Method and Periodic Convolution Layer

We verified that the deep learning method named reading periodic table introduced by ref. Deep Learning Model for Finding New Superconductors, which utilizes deep learning to read the periodic table and the laws of the elements, is applicable not only for superconductors, for which the method was originally applied but also for other problems of materials by demonstrating band gap estimations. We then extended the method to learn the laws better by directly learning the cylindrical periodicity between the right- and left-most columns in the periodic table at the learning representation level, that is, by considering the left- and right-most columns to be adjacent to each other. Thus, while the original method handles the table as is, the extended method treats the periodic table as if its two edges are connected. This is achieved using novel layers named periodic convolution layers, which can handle inputs exhibiting periodicity and may be applied to other problems related to computer vision, time series, and so on for data that possess some periodicity. In the reading periodic table method, no material feature or descriptor is required as input. We demonstrated two types of deep learning estimation: methods to estimate the existence of a bandgap, and methods to estimate the value of the bandgap given when the existence of the bandgap in the materials is known. Finally, we discuss the limitations of the dataset and model evaluation method. We may be unable to distinguish good models based on the random train-test split scheme; thus, we must prepare an appropriate dataset where the training and test data are temporally separate. The code and data are open.

arXiv:1912.05654

deepsing: Generating Sentiment-aware Visual Stories using Cross-modal Music Translation

In this paper we propose a deep learning method for performing attributed-based music-to-image translation. The proposed method is applied for synthesizing visual stories according to the sentiment expressed by songs. The generated images aim to induce the same feelings to the viewers, as the original song does, reinforcing the primary aim of music, i.e., communicating feelings. The process of music-to-image translation poses unique challenges, mainly due to the unstable mapping between the different modalities involved in this process. In this paper, we employ a trainable cross-modal translation method to overcome this limitation, leading to the first, to the best of our knowledge, deep learning method for generating sentiment-aware visual stories. Various aspects of the proposed method are extensively evaluated and discussed using different songs.

arXiv:1912.05687

REFINED (REpresentation of Features as Images with NEighborhood Dependencies): A novel feature representation for Convolutional Neural Networks

Deep learning with Convolutional Neural Networks has shown great promise in various areas of image-based classification and enhancement but is often unsuitable for predictive modeling involving non-image based features or features without spatial correlations. We present a novel approach for representation of high dimensional feature vector in a compact image form, termed REFINED (REpresentation of Features as Images with NEighborhood Dependencies), that is conducible for convolutional neural network based deep learning. We consider the correlations between features to generate a compact representation of the features in the form of a two-dimensional image using minimization of pairwise distances similar to multi-dimensional scaling. We hypothesize that this approach enables embedded feature selection and integrated with Convolutional Neural Network based Deep Learning can produce more accurate predictions as compared to Artificial Neural Networks, Random Forests and Support Vector Regression. We illustrate the superior predictive performance of the proposed representation, as compared to existing approaches, using synthetic datasets, cell line efficacy prediction based on drug chemical descriptors for NCI60 dataset and drug sensitivity prediction based on transcriptomic data and chemical descriptors using GDSC dataset. Results illustrated on both synthetic and biological datasets shows the higher prediction accuracy of the proposed framework as compared to existing methodologies while maintaining desirable properties in terms of bias and feature extraction.

arXiv:1912.06077

Understanding Important Features of Deep Learning Models for Transmission Electron Microscopy Image Segmentation

Cutting edge deep learning techniques allow for image segmentation with great speed and accuracy. However, application to problems in materials science is often difficult since these complex models may have difficultly learning physical parameters. In situ electron microscopy provides a clear platform for utilizing automated image analysis. In this work we consider the case of studying coarsening dynamics in supported nanoparticles, which is important for understanding e.g. the degradation of industrial catalysts. By systematically studying dataset preparation, neural network architecture, and accuracy evaluation, we describe important considerations in applying deep learning to physical applications, where generalizable and convincing models are required.

arXiv:1912.06075

Coronary Artery Plaque Characterization from CCTA Scans using Deep Learning and Radiomics

Assessing coronary artery plaque segments in coronary CT angiography scans is an important task to improve patient management and clinical outcomes, as it can help to decide whether invasive investigation and treatment are necessary. In this work, we present three machine learning approaches capable of performing this task. The first approach is based on radiomics, where a plaque segmentation is used to calculate various shape-, intensity- and texture-based features under different image transformations. A second approach is based on deep learning and relies on centerline extraction as sole prerequisite. In the third approach, we fuse the deep learning approach with radiomic features. On our data the methods reached similar scores as simulated fractional flow reserve (FFR) measurements, which - in contrast to our methods - requires an exact segmentation of the whole coronary tree and often time-consuming manual interaction. In literature, the performance of simulated FFR reaches an AUC between 0.79-0.93 predicting an abnormal invasive FFR that demands revascularization. The radiomics approach achieves an AUC of 0.86, the deep learning approach 0.84 and the combined method 0.88 for predicting the revascularization decision directly. While all three proposed methods can be determined within seconds, the FFR simulation typically takes several minutes. Provided representative training data in sufficient quantities, we believe that the presented methods can be used to create systems for fully automatic non-invasive risk assessment for a variety of adverse cardiac events.

arXiv:1912.05470

Human Gist Processing Augments Deep Learning Breast Cancer Risk Assessment

Radiologists can classify a mammogram as normal or abnormal at better than chance levels after less than a second's exposure to the images. In this work, we combine these radiologists' gist inputs into pre-trained machine learning models to validate that integrating gist with a CNN model can achieve an AUC (area under the curve) statistically significantly higher than either the gist perception of radiologists or the model without gist input.

arXiv:1912.05452

Solving the Reaction-Diffusion equation based on analytical methods and deep learning algorithm; the Case study of sulfate attack to concrete

The reaction-diffusion equation is one of the cornerstones equations in applied science and engineering. In the present study, a deep neural network has been trained in order to predict the solution of the equation with different coefficients using the numerical solution of this equation and the utility of deep learning. Analytical solution of the Reaction-Diffusion equation also has been conducted by taking advantage of the Danckwerts method. The accuracy of deep learning results was compared with the analytical solutions. In order to decrease the learning time and to find out similar equations solutions, such as pure diffusion and pure reaction, dimensional analysis technique has been performed. It was demonstrated that deep learning can accurately estimate the Partial Differential Equations solutionin the case of the reaction-diffusion equation with a constant coefficient.

arXiv:1912.05435

Deep Learning Methods for Signature Verification

Signature is widely used in human daily lives, and serves as a supplementary characteristic for verifying human identity. However, there is rare work of verifying signature. In this paper, we propose a few deep learning architectures to tackle this task, ranging from CNN, RNN to CNN-RNN compact model. We also improve Path Signature Features by encoding temporal information in order to enlarge the discrepancy between genuine and forgery signatures. Our numerical experiments demonstrate the effectiveness of our constructed models and features representations.

arXiv:1912.05012

Deep-Learning Assisted High-Resolution Binocular Stereo Depth Reconstruction

This work presents dense stereo reconstruction using high-resolution images for infrastructure inspections. The state-of-the-art stereo reconstruction methods, both learning and non-learning ones, consume too much computational resource on high-resolution data. Recent learning-based methods achieve top ranks on most benchmarks. However, they suffer from the generalization issue due to lack of task-specific training data. We propose to use a less resource demanding non-learning method, guided by a learning-based model, to handle high-resolution images and achieve accurate stereo reconstruction. The deep-learning model produces an initial disparity prediction with uncertainty for each pixel of the down-sampled stereo image pair. The uncertainty serves as a self-measurement of its generalization ability and the per-pixel searching range around the initially predicted disparity. The downstream process performs a modified version of the Semi-Global Block Matching method with the up-sampled per-pixel searching range. The proposed deep-learning assisted method is evaluated on the Middlebury dataset and high-resolution stereo images collected by our customized binocular stereo camera. The combination of learning and non-learning methods achieves better performance on 12 out of 15 cases of the Middlebury dataset. In our infrastructure inspection experiments, the average 3D reconstruction error is less than 0.004m.

arXiv:1912.04754

Deep Latent Factor Model for Collaborative Filtering

Latent factor models have been used widely in collaborative filtering based recommender systems. In recent years, deep learning has been successful in solving a wide variety of machine learning problems. Motivated by the success of deep learning, we propose a deeper version of latent factor model. Experiments on benchmark datasets shows that our proposed technique significantly outperforms all state-of-the-art collaborative filtering techniques.

arXiv:1912.04711

End-to-end facial and physiological model for Affective Computing and applications

In recent years, Affective Computing and its applications have become a fast-growing research topic. Furthermore, the rise of Deep Learning has introduced significant improvements in the emotion recognition system compared to classical methods. In this work, we propose a multi-modal emotion recognition model based on deep learning techniques using the combination of peripheral physiological signals and facial expressions. Moreover, we present an improvement to proposed models by introducing latent features extracted from our internal Bio Auto-Encoder (BAE). Both models are trained and evaluated on AMIGOS datasets reporting valence, arousal, and emotion state classification. Finally, to demonstrate a possible medical application in affective computing using deep learning techniques, we applied the proposed method to the assessment of anxiety therapy. To this purpose, a reduced multi-modal database has been collected by recording facial expressions and peripheral signals such as Electrocardiogram (ECG) and Galvanic Skin Response (GSR) of each patient. Valence and arousal estimation was extracted using the proposed model from the beginning until the end of the therapy, with successful evaluation to the different emotional changes in the temporal domain.

arXiv:1912.04471공식 코드 · Papers with Code

Duet at TREC 2019 Deep Learning Track

This report discusses three submissions based on the Duet architecture to the Deep Learning track at TREC 2019. For the document retrieval task, we adapt the Duet model to ingest a "multiple field" view of documents---we refer to the new architecture as Duet with Multiple Fields (DuetMF). A second submission combines the DuetMF model with other neural and traditional relevance estimators in a learning-to-rank framework and achieves improved performance over the DuetMF baseline. For the passage retrieval task, we submit a single run based on an ensemble of eight Duet models.

arXiv:1912.04357공식 코드 · Papers with Code

DeepMUSIC: Multiple Signal Classification via Deep Learning

This letter introduces a deep learning (DL) framework for direction-of-arrival (DOA) estimation. Previous works in DL context mostly consider a single or two target scenario which is a strong limitation in practice. Hence, in this work, we propose a DL framework for multiple signal classification (DeepMUSIC). We design multiple deep convolutional neural networks (CNNs), each of which is dedicated to a subregion of the angular spectrum. In particular, each CNN is fed with the array covariance matrix and it learns the MUSIC spectra of the corresponding angular subregion. We have shown, through simulations, that the proposed DeepMUSIC framework has superior estimation accuracy and exhibits less computational complexity in comparison with both DL and non-DL based techniques.

arXiv:1912.05156

Lifelong learning for text retrieval and recognition in historical handwritten document collections

This chapter provides an overview of the problems that need to be dealt with when constructing a lifelong-learning retrieval, recognition and indexing engine for large historical document collections in multiple scripts and languages, the Monk system. This application is highly variable over time, since the continuous labeling by end users changes the concept of what a 'ground truth' constitutes. Although current advances in deep learning provide a huge potential in this application domain, the scale of the problem, i.e., more than 520 hugely diverse books, documents and manuscripts precludes the current meticulous and painstaking human effort which is required in designing and developing successful deep-learning systems. The ball-park principle is introduced, which describes the evolution from the sparsely-labeled stage that can only be addressed by traditional methods or nearest-neighbor methods on embedded vectors of pre-trained neural networks, up to the other end of the spectrum where massive labeling allows reliable training of deep-learning methods. Contents: Introduction, Expectation management, Deep learning, The ball-park principle, Technical realization, Work flow, Quality and quantity of material, Industrialization and scalability, Human effort, Algorithms, Object of recognition, Processing pipeline, Performance,Compositionality, Conclusion.

arXiv:1912.04822공식 코드 · Papers with Code

libmolgrid: GPU Accelerated Molecular Gridding for Deep Learning Applications

There are many ways to represent a molecule as input to a machine learning model and each is associated with loss and retention of certain kinds of information. In the interest of preserving three-dimensional spatial information, including bond angles and torsions, we have developed libmolgrid, a general-purpose library for representing three-dimensional molecules using multidimensional arrays. This library also provides functionality for composing batches of data suited to machine learning workflows, including data augmentation, class balancing, and example stratification according to a regression variable or data subgroup, and it further supports temporal and spatial recurrences over that data to facilitate work with recurrent neural networks, dynamical data, and size extensive modeling. It was designed for seamless integration with popular deep learning frameworks, including Caffe, PyTorch, and Keras, providing good performance by leveraging graphical processing units (GPUs) for computationally-intensive tasks and efficient memory usage through the use of memory views over preallocated buffers. libmolgrid is a free and open source project that is actively supported, serving the growing need in the molecular modeling community for tools that streamline the process of data ingestion, representation construction, and principled machine learning model development.

arXiv:1912.04481

SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads

In recent years, there has been tremendous advances in hardware acceleration of deep neural networks. However, most of the research has focused on optimizing accelerator microarchitecture for higher performance and energy efficiency on a per-layer basis. We find that for overall single-batch inference latency, the accelerator may only make up 25-40%, with the rest spent on data movement and in the deep learning software framework. Thus far, it has been very difficult to study end-to-end DNN performance during early stage design (before RTL is available) because there are no existing DNN frameworks that support end-to-end simulation with easy custom hardware accelerator integration. To address this gap in research infrastructure, we present SMAUG, the first DNN framework that is purpose-built for simulation of end-to-end deep learning applications. SMAUG offers researchers a wide range of capabilities for evaluating DNN workloads, from diverse network topologies to easy accelerator modeling and SoC integration. To demonstrate the power and value of SMAUG, we present case studies that show how we can optimize overall performance and energy efficiency for up to 1.8-5x speedup over a baseline system, without changing any part of the accelerator microarchitecture, as well as show how SMAUG can tune an SoC for a camera-powered deep learning pipeline.