January 30, 2020

3298 words 16 mins read

Paper Group ANR 408

Deep Learning Reveals Underlying Physics of Light-matter Interactions in Nanophotonic Devices. Continual Prediction from EHR Data for Inpatient Acute Kidney Injury. Datalog Reasoning over Compressed RDF Knowledge Bases. Synthesizing facial photometries and corresponding geometries using generative adversarial networks. Barnes-Hut Approximation for …

Deep Learning Reveals Underlying Physics of Light-matter Interactions in Nanophotonic Devices


Title	Deep Learning Reveals Underlying Physics of Light-matter Interactions in Nanophotonic Devices
Authors	Yashar Kiarashinejad, Sajjad Abdollahramezani, Mohammadreza Zandehshahvar, Omid Hemmatyar, Ali Adibi
Abstract	In this paper, we present a deep learning-based (DL-based) algorithm, as a purely mathematical platform, for providing intuitive understanding of the properties of electromagnetic (EM) wave-matter interaction in nanostructures. This approach is based on using the dimensionality reduction (DR) technique to significantly reduce the dimensionality of a generic EM wave-matter interaction problem without imposing significant error. Such an approach implicitly provides useful information about the role of different features (or design parameters such as geometry) of the nanostructure in its response functionality. To demonstrate the practical capabilities of this DL-based technique, we apply it to a reconfigurable optical metadevice enabling dual-band and triple-band optical absorption in the telecommunication window. Combination of the proposed approach with existing commercialized full-wave simulation tools offers a powerful toolkit to extract basic mechanisms of wave-matter interaction in complex EM devices and facilitate the design and optimization of nanostructures for a large range of applications including imaging, spectroscopy, and signal processing. It is worth to mention that the demonstrated approach is general and can be used in a large range of problems as long as enough training data can be provided.
Tasks	Dimensionality Reduction
Published	2019-05-07
URL	https://arxiv.org/abs/1905.06889v1
PDF	https://arxiv.org/pdf/1905.06889v1.pdf
PWC	https://paperswithcode.com/paper/190506889
Repo
Framework

Continual Prediction from EHR Data for Inpatient Acute Kidney Injury


Title	Continual Prediction from EHR Data for Inpatient Acute Kidney Injury
Authors	Rohit J. Kate, Noah Pearce, Debesh Mazumdar, Vani Nilakantan
Abstract	Acute kidney injury (AKI) commonly occurs in hospitalized patients and can lead to serious medical complications. In order to optimally predict AKI before it develops at any time during a hospital stay, we present a novel framework in which AKI is continually predicted automatically from EHR data over the entire hospital stay instead of at only one particular time. The continual model predicts AKI every time a patients AKI-relevant variable changes in the EHR. Thus the model is not only independent of a particular time for making predictions, but it can also leverage the latest values of all the AKI-relevant patient variables for making predictions. Using data of 44,691 hospital stays of duration longer than 24 hours we evaluated our continual prediction model and compared it with the traditional one-time prediction models. Excluding hospitals stays in which AKI occurred within 24 hours from admission, the one-time prediction model predicting at 24 hours from admission obtained area under ROC curve (AUC) of 0.653 while the continual prediction model obtained AUC of 0.724. The one-time prediction model that predicts at 24 hours obviously cannot predict AKI incidences that occur within 24 hours of admission which when included in the evaluation reduced its AUC to 0.57. In comparison, the continual prediction model had AUC of 0.709. The continual prediction model also did better than all other one-time prediction models predicting at other fixed times. By being able to take into account the latest values of AKI-relevant patient variables and by not being limited to a particular time of prediction, the continual prediction model out-performed one-time prediction models in predicting AKI.
Tasks
Published	2019-02-26
URL	http://arxiv.org/abs/1902.10228v1
PDF	http://arxiv.org/pdf/1902.10228v1.pdf
PWC	https://paperswithcode.com/paper/continual-prediction-from-ehr-data-for
Repo
Framework

Datalog Reasoning over Compressed RDF Knowledge Bases


Title	Datalog Reasoning over Compressed RDF Knowledge Bases
Authors	Pan Hu, Jacopo Urbani, Boris Motik, Ian Horrocks
Abstract	Materialisation is often used in RDF systems as a preprocessing step to derive all facts implied by given RDF triples and rules. Although widely used, materialisation considers all possible rule applications and can use a lot of memory for storing the derived facts, which can hinder performance. We present a novel materialisation technique that compresses the RDF triples so that the rules can sometimes be applied to multiple facts at once, and the derived facts can be represented using structure sharing. Our technique can thus require less space, as well as skip certain rule applications. Our experiments show that our technique can be very effective: when the rules are relatively simple, our system is both faster and requires less memory than prominent state-of-the-art RDF systems.
Tasks
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10177v2
PDF	https://arxiv.org/pdf/1908.10177v2.pdf
PWC	https://paperswithcode.com/paper/datalog-reasoning-over-compressed-rdf
Repo
Framework

Synthesizing facial photometries and corresponding geometries using generative adversarial networks


Title	Synthesizing facial photometries and corresponding geometries using generative adversarial networks
Authors	Gil Shamai, Ron Slossberg, Ron Kimmel
Abstract	Artificial data synthesis is currently a well studied topic with useful applications in data science, computer vision, graphics and many other fields. Generating realistic data is especially challenging since human perception is highly sensitive to non realistic appearance. In recent times, new levels of realism have been achieved by advances in GAN training procedures and architectures. These successful models, however, are tuned mostly for use with regularly sampled data such as images, audio and video. Despite the successful application of the architecture on these types of media, applying the same tools to geometric data poses a far greater challenge. The study of geometric deep learning is still a debated issue within the academic community as the lack of intrinsic parametrization inherent to geometric objects prohibits the direct use of convolutional filters, a main building block of today’s machine learning systems. In this paper we propose a new method for generating realistic human facial geometries coupled with overlayed textures. We circumvent the parametrization issue by imposing a global mapping from our data to the unit rectangle. We further discuss how to design such a mapping to control the mapping distortion and conserve area within the mapped image. By representing geometric textures and geometries as images, we are able to use advanced GAN methodologies to generate new geometries. We address the often neglected topic of relation between texture and geometry and propose to use this correlation to match between generated textures and their corresponding geometries. We offer a new method for training GAN models on partially corrupted data. Finally, we provide empirical evidence demonstrating our generative model’s ability to produce examples of new identities independent from the training data while maintaining a high level of realism, two traits that are often at odds.
Tasks
Published	2019-01-19
URL	http://arxiv.org/abs/1901.06551v1
PDF	http://arxiv.org/pdf/1901.06551v1.pdf
PWC	https://paperswithcode.com/paper/synthesizing-facial-photometries-and
Repo
Framework

Barnes-Hut Approximation for Point SetGeodesic Shooting


Title	Barnes-Hut Approximation for Point SetGeodesic Shooting
Authors	Jiancong Wang, Long Xie, Paul Yushkevich, James Gee
Abstract	Geodesic shooting has been successfully applied to diffeo-morphic registration of point sets. Exact computation of the geodesicshooting between point sets, however, requiresO(N2) calculations each time step on the number of points in the point set. We proposean approximation approach based on the Barnes-Hut algorithm to speedup point set geodesic shooting. This approximation can reduce the al-gorithm complexity toO(N b+N logN). The evaluation of the proposedmethod in both simulated images and the medial temporal lobe thick-ness analysis demonstrates a comparable accuracy to the exact point set geodesic shooting while offering up to 3-fold speed up. This improvementopens up a range of clinical research studies and practical problems towhich the method can be effectively applied.
Tasks
Published	2019-07-10
URL	https://arxiv.org/abs/1907.04834v1
PDF	https://arxiv.org/pdf/1907.04834v1.pdf
PWC	https://paperswithcode.com/paper/barnes-hut-approximation-for-point
Repo
Framework

Understanding the One-Pixel Attack: Propagation Maps and Locality Analysis


Title	Understanding the One-Pixel Attack: Propagation Maps and Locality Analysis
Authors	Danilo Vasconcellos Vargas, Jiawei Su
Abstract	Deep neural networks were shown to be vulnerable to single pixel modifications. However, the reason behind such phenomena has never been elucidated. Here, we propose Propagation Maps which show the influence of the perturbation in each layer of the network. Propagation Maps reveal that even in extremely deep networks such as Resnet, modification in one pixel easily propagates until the last layer. In fact, this initial local perturbation is also shown to spread becoming a global one and reaching absolute difference values that are close to the maximum value of the original feature maps in a given layer. Moreover, we do a locality analysis in which we demonstrate that nearby pixels of the perturbed one in the one-pixel attack tend to share the same vulnerability, revealing that the main vulnerability lies in neither neurons nor pixels but receptive fields. Hopefully, the analysis conducted in this work together with a new technique called propagation maps shall shed light into the inner workings of other adversarial samples and be the basis of new defense systems to come.
Tasks
Published	2019-02-08
URL	http://arxiv.org/abs/1902.02947v1
PDF	http://arxiv.org/pdf/1902.02947v1.pdf
PWC	https://paperswithcode.com/paper/understanding-the-one-pixel-attack
Repo
Framework

Fast and Differentiable Message Passing for Stereo Vision


Title	Fast and Differentiable Message Passing for Stereo Vision
Authors	Zhiwei Xu, Thalaiyasingam Ajanthan, Richard Hartley
Abstract	Despite the availability of many Markov Random Field (MRF) optimization algorithms, their widespread usage is currently limited due to imperfect MRF modelling arising from hand-crafted model parameters. In addition to differentiability, the two main aspects that enable learning these model parameters are the forward and backward propagation time of the MRF optimization algorithm and its parallelization capabilities. In this work, we introduce two fast and differentiable message passing algorithms, namely, Iterative Semi-Global Matching Revised (ISGMR) and Parallel Tree-Reweighted Message Passing (TRWP) which are greatly sped up on GPU by exploiting massive parallelism. Specifically, ISGMR is an iterative and revised version of the standard SGM for general second-order MRFs with improved optimization effectiveness, whereas TRWP is a highly parallelizable version of Sequential TRW (TRWS) for faster optimization. Our experiments on standard stereo benchmarks demonstrate that ISGMR achieves much lower energies than SGM and TRWP is two orders of magnitude faster than TRWS without losing effectiveness in optimization. Furthermore, our CUDA implementations are at least 7 and 650 times faster than PyTorch GPU implementations in the forward and backward propagation, respectively, enabling efficient end-to-end learning with message passing.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10892v2
PDF	https://arxiv.org/pdf/1910.10892v2.pdf
PWC	https://paperswithcode.com/paper/fast-and-differentiable-message-passing-for
Repo
Framework

Breast mass classification in ultrasound based on Kendall’s shape manifold


Title	Breast mass classification in ultrasound based on Kendall’s shape manifold
Authors	Michal Byra, Michael Andre
Abstract	Morphological features play an important role in breast mass classification in sonography. While benign breast masses tend to have a well-defined ellipsoidal contour, shape of malignant breast masses is commonly ill-defined and highly variable. Various handcrafted morphological features have been developed over the years to assess this phenomenon and help the radiologists differentiate benign and malignant masses. In this paper we propose an automatic approach to morphology analysis, we express shapes of breast masses as points on the Kendall’s shape manifold. Next, we use the full Procrustes distance to develop support vector machine classifiers for breast mass differentiation. The usefulness of our method is demonstrated using a dataset of B-mode images collected from 163 breast masses. Our method achieved area under the receiver operating characteristic curve of 0.81. The proposed method can be used to assess shapes of breast masses in ultrasound without any feature engineering.
Tasks	Feature Engineering
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11159v1
PDF	https://arxiv.org/pdf/1905.11159v1.pdf
PWC	https://paperswithcode.com/paper/breast-mass-classification-in-ultrasound
Repo
Framework

Is a single unique Bayesian network enough to accurately represent your data?


Title	Is a single unique Bayesian network enough to accurately represent your data?
Authors	Gilles Kratzer, Reinhard Furrer
Abstract	Bayesian network (BN) modelling is extensively used in systems epidemiology. Usually it consists in selecting and reporting the best-fitting structure conditional to the data. A major practical concern is avoiding overfitting, on account of its extreme flexibility and its modelling richness. Many approaches have been proposed to control for overfitting. Unfortunately, they essentially all rely on very crude decisions that result in too simplistic approaches for such complex systems. In practice, with limited data sampled from complex system, this approach seems too simplistic. An alternative would be to use the Monte Carlo Markov chain model choice (MC3) over the network to learn the landscape of reasonably supported networks, and then to present all possible arcs with their MCMC support. This paper presents an R implementation, called mcmcabn, of a flexible structural MC3 that is accessible to non-specialists.
Tasks	Epidemiology
Published	2019-02-18
URL	http://arxiv.org/abs/1902.06641v1
PDF	http://arxiv.org/pdf/1902.06641v1.pdf
PWC	https://paperswithcode.com/paper/is-a-single-unique-bayesian-network-enough-to
Repo
Framework

A deep learning model for segmentation of geographic atrophy to study its long-term natural history


Title	A deep learning model for segmentation of geographic atrophy to study its long-term natural history
Authors	Bart Liefers, Johanna M. Colijn, Cristina González-Gonzalo, Timo Verzijden, Paul Mitchell, Carel B. Hoyng, Bram van Ginneken, Caroline C. W. Klaver, Clara I. Sánchez
Abstract	Purpose: To develop and validate a deep learning model for automatic segmentation of geographic atrophy (GA) in color fundus images (CFIs) and its application to study growth rate of GA. Participants: 409 CFIs of 238 eyes with GA from the Rotterdam Study (RS) and the Blue Mountain Eye Study (BMES) for model development, and 5,379 CFIs of 625 eyes from the Age-Related Eye Disease Study (AREDS) for analysis of GA growth rate. Methods: A deep learning model based on an ensemble of encoder-decoder architectures was implemented and optimized for the segmentation of GA in CFIs. Four experienced graders delineated GA in CFIs from RS and BMES. These manual delineations were used to evaluate the segmentation model using 5-fold cross-validation. The model was further applied to CFIs from the AREDS to study the growth rate of GA. Linear regression analysis was used to study associations between structural biomarkers at baseline and GA growth rate. A general estimate of the progression of GA area over time was made by combining growth rates of all eyes with GA from the AREDS set. Results: The model obtained an average Dice coefficient of 0.72 $\pm$ 0.26 on the BMES and RS. An intraclass correlation coefficient of 0.83 was reached between the automatically estimated GA area and the graders’ consensus measures. Eight automatically calculated structural biomarkers (area, filled area, convex area, convex solidity, eccentricity, roundness, foveal involvement and perimeter) were significantly associated with growth rate. Combining all growth rates indicated that GA area grows quadratically up to an area of around 12 mm$^{2}$, after which growth rate stabilizes or decreases. Conclusion: The presented deep learning model allowed for fully automatic and robust segmentation of GA in CFIs. These segmentations can be used to extract structural characteristics of GA that predict its growth rate.
Tasks
Published	2019-08-15
URL	https://arxiv.org/abs/1908.05621v1
PDF	https://arxiv.org/pdf/1908.05621v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-model-for-segmentation-of
Repo
Framework

Char-RNN for Word Stress Detection in East Slavic Languages


Title	Char-RNN for Word Stress Detection in East Slavic Languages
Authors	Ekaterina Chernyak, Maria Ponomareva, Kirill Milintsevich
Abstract	We explore how well a sequence labeling approach, namely, recurrent neural network, is suited for the task of resource-poor and POS tagging free word stress detection in the Russian, Ukranian, Belarusian languages. We present new datasets, annotated with the word stress, for the three languages and compare several RNN models trained on three languages and explore possible applications of the transfer learning for the task. We show that it is possible to train a model in a cross-lingual setting and that using additional languages improves the quality of the results.
Tasks	Transfer Learning
Published	2019-06-10
URL	https://arxiv.org/abs/1906.04082v1
PDF	https://arxiv.org/pdf/1906.04082v1.pdf
PWC	https://paperswithcode.com/paper/char-rnn-for-word-stress-detection-in-east-1
Repo
Framework

Robust Neural Machine Translation with Doubly Adversarial Inputs


Title	Robust Neural Machine Translation with Doubly Adversarial Inputs
Authors	Yong Cheng, Lu Jiang, Wolfgang Macherey
Abstract	Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the translation model with adversarial source examples; (2) defend the translation model with adversarial target inputs to improve its robustness against the adversarial source inputs.For the generation of adversarial inputs, we propose a gradient-based method to craft adversarial examples informed by the translation loss over the clean inputs.Experimental results on Chinese-English and English-German translation tasks demonstrate that our approach achieves significant improvements ($2.8$ and $1.6$ BLEU points) over Transformer on standard clean benchmarks as well as exhibiting higher robustness on noisy data.
Tasks	Machine Translation
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02443v1
PDF	https://arxiv.org/pdf/1906.02443v1.pdf
PWC	https://paperswithcode.com/paper/robust-neural-machine-translation-with-doubly
Repo
Framework

Metamorphic Detection of Adversarial Examples in Deep Learning Models With Affine Transformations


Title	Metamorphic Detection of Adversarial Examples in Deep Learning Models With Affine Transformations
Authors	Rohan Reddy Mekala, Gudjon Einar Magnusson, Adam Porter, Mikael Lindvall, Madeline Diep
Abstract	Adversarial attacks are small, carefully crafted perturbations, imperceptible to the naked eye; that when added to an image cause deep learning models to misclassify the image with potentially detrimental outcomes. With the rise of artificial intelligence models in consumer safety and security intensive industries such as self-driving cars, camera surveillance and face recognition, there is a growing need for guarding against adversarial attacks. In this paper, we present an approach that uses metamorphic testing principles to automatically detect such adversarial attacks. The approach can detect image manipulations that are so small, that they are impossible to detect by a human through visual inspection. By applying metamorphic relations based on distance ratio preserving affine image transformations which compare the behavior of the original and transformed image; we show that our proposed approach can determine whether or not the input image is adversarial with a high degree of accuracy.
Tasks	Face Recognition, Self-Driving Cars
Published	2019-07-10
URL	https://arxiv.org/abs/1907.04774v1
PDF	https://arxiv.org/pdf/1907.04774v1.pdf
PWC	https://paperswithcode.com/paper/metamorphic-detection-of-adversarial-examples
Repo
Framework

On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning


Title	On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning
Authors	Bharat Prakash, Mark Horton, {Nicholas R. Waytowich, William David Hairston, Tim Oates, Tinoosh Mohsenin
Abstract	In autonomous embedded systems, it is often vital to reduce the amount of actions taken in the real world and energy required to learn a policy. Training reinforcement learning agents from high dimensional image representations can be very expensive and time consuming. Autoencoders are deep neural network used to compress high dimensional data such as pixelated images into small latent representations. This compression model is vital to efficiently learn policies, especially when learning on embedded systems. We have implemented this model on the NVIDIA Jetson TX2 embedded GPU, and evaluated the power consumption, throughput, and energy consumption of the autoencoders for various CPU/GPU core combinations, frequencies, and model parameters. Additionally, we have shown the reconstructions generated by the autoencoder to analyze the quality of the generated compressed representation and also the performance of the reinforcement learning agent. Finally, we have presented an assessment of the viability of training these models on embedded systems and their usefulness in developing autonomous policies. Using autoencoders, we were able to achieve 4-5 $\times$ improved performance compared to a baseline RL agent with a convolutional feature extractor, while using less than 2W of power.
Tasks
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10404v1
PDF	http://arxiv.org/pdf/1903.10404v1.pdf
PWC	https://paperswithcode.com/paper/on-the-use-of-deep-autoencoders-for-efficient
Repo
Framework

Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model


Title	Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model
Authors	Anjuli Kannan, Arindrima Datta, Tara N. Sainath, Eugene Weinstein, Bhuvana Ramabhadran, Yonghui Wu, Ankur Bapna, Zhifeng Chen, Seungji Lee
Abstract	Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world’s languages. They have shown improvement over monolingual systems, and have simplified training and serving by eliminating language-specific acoustic, pronunciation, and language models. This work presents an E2E multilingual system which is equipped to operate in low-latency interactive applications, as well as handle a key challenge of real world data: the imbalance in training data across languages. Using nine Indic languages, we compare a variety of techniques, and find that a combination of conditioning on a language vector and training language-specific adapter layers produces the best model. The resulting E2E multilingual model achieves a lower word error rate (WER) than both monolingual E2E models (eight of nine languages) and monolingual conventional systems (all nine languages).
Tasks	Speech Recognition
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05330v1
PDF	https://arxiv.org/pdf/1909.05330v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-multilingual-speech-recognition
Repo
Framework