Paper Group ANR 763
Entrenamiento de una red neuronal para el reconocimiento de imagenes de lengua de senas capturadas con sensores de profundidad. Model parameter estimation using coherent structure coloring. What do Deep Networks Like to See?. Time is of the Essence: Machine Learning-based Intrusion Detection in Industrial Time Series Data. The Rule of Three: Abstra …
Entrenamiento de una red neuronal para el reconocimiento de imagenes de lengua de senas capturadas con sensores de profundidad
Title | Entrenamiento de una red neuronal para el reconocimiento de imagenes de lengua de senas capturadas con sensores de profundidad |
Authors | Rivas P. Pedro E., Velarde-Anaya Omar, Gonzalez-Lopez Samuel, Rivas P. Pablo, Alvarez-Torres Norma Angelica |
Abstract | Due to the growth of the population with hearing problems, devices have been developed that facilitate the inclusion of deaf people in society, using technology as a communication tool, such as vision systems. Then, a solution to this problem is presented using neural networks and autoencoders for the classification of American Sign Language images. As a result, 99.5% accuracy and an error of 0.01684 were obtained for image classification |
Tasks | Image Classification |
Published | 2018-03-22 |
URL | http://arxiv.org/abs/1804.00508v1 |
http://arxiv.org/pdf/1804.00508v1.pdf | |
PWC | https://paperswithcode.com/paper/entrenamiento-de-una-red-neuronal-para-el |
Repo | |
Framework | |
Model parameter estimation using coherent structure coloring
Title | Model parameter estimation using coherent structure coloring |
Authors | Kristy L. Schlueter-Kuck, John O. Dabiri |
Abstract | Lagrangian data assimilation is a complex problem in oceanic and atmospheric modeling. Tracking drifters in large-scale geophysical flows can involve uncertainty in drifter location, complex inertial effects, and other factors which make comparing them to simulated Lagrangian trajectories from numerical models extremely challenging. Temporal and spatial discretization, factors necessary in modeling large scale flows, also contribute to separation between real and simulated drifter trajectories. The chaotic advection inherent in these turbulent flows tends to separate even closely spaced tracer particles, making error metrics based solely on drifter displacements unsuitable for estimating model parameters. We propose to instead use error in the coherent structure coloring (CSC) field to assess model skill. The CSC field provides a spatial representation of the underlying coherent patterns in the flow, and we show that it is a more robust metric for assessing model accuracy. Through the use of two test cases, one considering spatial uncertainty in particle initialization, and one examining the influence of stochastic error along a trajectory and temporal discretization, we show that error in the coherent structure coloring field can be used to accurately determine single or multiple simultaneously unknown model parameters, whereas a conventional error metric based on error in drifter displacement fails. Because the CSC field enhances the difference in error between correct and incorrect model parameters, error minima in model parameter sweeps become more distinct. The effectiveness and robustness of this method for single and multi-parameter estimation in analytical flows suggests that Lagrangian data assimilation for real oceanic and atmospheric models would benefit from a similar approach. |
Tasks | |
Published | 2018-10-31 |
URL | http://arxiv.org/abs/1810.13444v1 |
http://arxiv.org/pdf/1810.13444v1.pdf | |
PWC | https://paperswithcode.com/paper/model-parameter-estimation-using-coherent |
Repo | |
Framework | |
What do Deep Networks Like to See?
Title | What do Deep Networks Like to See? |
Authors | Sebastian Palacio, Joachim Folz, Jörn Hees, Federico Raue, Damian Borth, Andreas Dengel |
Abstract | We propose a novel way to measure and understand convolutional neural networks by quantifying the amount of input signal they let in. To do this, an autoencoder (AE) was fine-tuned on gradients from a pre-trained classifier with fixed parameters. We compared the reconstructed samples from AEs that were fine-tuned on a set of image classifiers (AlexNet, VGG16, ResNet-50, and Inception~v3) and found substantial differences. The AE learns which aspects of the input space to preserve and which ones to ignore, based on the information encoded in the backpropagated gradients. Measuring the changes in accuracy when the signal of one classifier is used by a second one, a relation of total order emerges. This order depends directly on each classifier’s input signal but it does not correlate with classification accuracy or network size. Further evidence of this phenomenon is provided by measuring the normalized mutual information between original images and auto-encoded reconstructions from different fine-tuned AEs. These findings break new ground in the area of neural network understanding, opening a new way to reason, debug, and interpret their results. We present four concrete examples in the literature where observations can now be explained in terms of the input signal that a model uses. |
Tasks | |
Published | 2018-03-22 |
URL | http://arxiv.org/abs/1803.08337v1 |
http://arxiv.org/pdf/1803.08337v1.pdf | |
PWC | https://paperswithcode.com/paper/what-do-deep-networks-like-to-see |
Repo | |
Framework | |
Time is of the Essence: Machine Learning-based Intrusion Detection in Industrial Time Series Data
Title | Time is of the Essence: Machine Learning-based Intrusion Detection in Industrial Time Series Data |
Authors | Simon Duque Anton, Lia Ahrens, Daniel Fraunholz, Hans Dieter Schotten |
Abstract | The Industrial Internet of Things drastically increases connectivity of devices in industrial applications. In addition to the benefits in efficiency, scalability and ease of use, this creates novel attack surfaces. Historically, industrial networks and protocols do not contain means of security, such as authentication and encryption, that are made necessary by this development. Thus, industrial IT-security is needed. In this work, emulated industrial network data is transformed into a time series and analysed with three different algorithms. The data contains labeled attacks, so the performance can be evaluated. Matrix Profiles perform well with almost no parameterisation needed. Seasonal Autoregressive Integrated Moving Average performs well in the presence of noise, requiring parameterisation effort. Long Short Term Memory-based neural networks perform mediocre while requiring a high training- and parameterisation effort. |
Tasks | Intrusion Detection, Time Series |
Published | 2018-09-20 |
URL | http://arxiv.org/abs/1809.07500v1 |
http://arxiv.org/pdf/1809.07500v1.pdf | |
PWC | https://paperswithcode.com/paper/time-is-of-the-essence-machine-learning-based |
Repo | |
Framework | |
The Rule of Three: Abstractive Text Summarization in Three Bullet Points
Title | The Rule of Three: Abstractive Text Summarization in Three Bullet Points |
Authors | Tomonori Kodaira, Mamoru Komachi |
Abstract | Neural network-based approaches have become widespread for abstractive text summarization. Though previously proposed models for abstractive text summarization addressed the problem of repetition of the same contents in the summary, they did not explicitly consider its information structure. One of the reasons these previous models failed to account for information structure in the generated summary is that standard datasets include summaries of variable lengths, resulting in problems in analyzing information flow, specifically, the manner in which the first sentence is related to the following sentences. Therefore, we use a dataset containing summaries with only three bullet points, and propose a neural network-based abstractive summarization model that considers the information structures of the generated summaries. Our experimental results show that the information structure of a summary can be controlled, thus improving the performance of the overall summarization. |
Tasks | Abstractive Text Summarization, Text Summarization |
Published | 2018-09-28 |
URL | http://arxiv.org/abs/1809.10867v1 |
http://arxiv.org/pdf/1809.10867v1.pdf | |
PWC | https://paperswithcode.com/paper/the-rule-of-three-abstractive-text |
Repo | |
Framework | |
4D Human Body Correspondences from Panoramic Depth Maps
Title | 4D Human Body Correspondences from Panoramic Depth Maps |
Authors | Zhong Li, Minye Wu, Wangyiteng Zhou, Jingyi Yu |
Abstract | The availability of affordable 3D full body reconstruction systems has given rise to free-viewpoint video (FVV) of human shapes. Most existing solutions produce temporally uncorrelated point clouds or meshes with unknown point/vertex correspondences. Individually compressing each frame is ineffective and still yields to ultra-large data sizes. We present an end-to-end deep learning scheme to establish dense shape correspondences and subsequently compress the data. Our approach uses sparse set of “panoramic” depth maps or PDMs, each emulating an inward-viewing concentric mosaics. We then develop a learning-based technique to learn pixel-wise feature descriptors on PDMs. The results are fed into an autoencoder-based network for compression. Comprehensive experiments demonstrate our solution is robust and effective on both public and our newly captured datasets. |
Tasks | |
Published | 2018-10-12 |
URL | http://arxiv.org/abs/1810.05340v1 |
http://arxiv.org/pdf/1810.05340v1.pdf | |
PWC | https://paperswithcode.com/paper/4d-human-body-correspondences-from-panoramic |
Repo | |
Framework | |
Gradient conjugate priors and multi-layer neural networks
Title | Gradient conjugate priors and multi-layer neural networks |
Authors | Pavel Gurevich, Hannes Stuke |
Abstract | The paper deals with learning probability distributions of observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for neural networks, which is a modification of the classical Bayesian update for conjugate priors. We establish a connection between the gradient conjugate prior update and the maximization of the log-likelihood of the predictive distribution. Unlike for the Bayesian neural networks, we use deterministic weights of neural networks, but rather assume that the ground truth distribution is normal with unknown mean and variance and learn by the neural networks the parameters of a prior (normal-gamma distribution) for these unknown mean and variance. The update of the parameters is done, using the gradient that, at each step, directs towards minimizing the Kullback–Leibler divergence from the prior to the posterior distribution (both being normal-gamma). We obtain a corresponding dynamical system for the prior’s parameters and analyze its properties. In particular, we study the limiting behavior of all the prior’s parameters and show how it differs from the case of the classical full Bayesian update. The results are validated on synthetic and real world data sets. |
Tasks | |
Published | 2018-02-07 |
URL | http://arxiv.org/abs/1802.02643v3 |
http://arxiv.org/pdf/1802.02643v3.pdf | |
PWC | https://paperswithcode.com/paper/gradient-conjugate-priors-and-multi-layer |
Repo | |
Framework | |
A unifying Bayesian approach for preterm brain-age prediction that models EEG sleep transitions over age
Title | A unifying Bayesian approach for preterm brain-age prediction that models EEG sleep transitions over age |
Authors | Kirubin Pillay, Maarten De Vos |
Abstract | Preterm newborns undergo various stresses that may materialize as learning problems at school-age. Sleep staging of the Electroencephalogram (EEG), followed by prediction of their brain-age from these sleep states can quantify deviations from normal brain development early (when compared to the known age). Current automation of this approach relies on explicit sleep state classification, optimizing algorithms using clinician visually labelled sleep stages, which remains a subjective gold-standard. Such models fail to perform consistently over a wide age range and impacts the subsequent brain-age estimates that could prevent identification of subtler developmental deviations. We introduce a Bayesian Network utilizing multiple Gaussian Mixture Models, as a novel, unified approach for directly estimating brain-age, simultaneously modelling for both age and sleep dependencies on the EEG, to improve the accuracy of prediction over a wider age range. |
Tasks | EEG |
Published | 2018-09-19 |
URL | http://arxiv.org/abs/1809.07102v1 |
http://arxiv.org/pdf/1809.07102v1.pdf | |
PWC | https://paperswithcode.com/paper/a-unifying-bayesian-approach-for-preterm |
Repo | |
Framework | |
Causal Inference for Early Detection of Pathogenic Social Media Accounts
Title | Causal Inference for Early Detection of Pathogenic Social Media Accounts |
Authors | Hamidreza Alvari, Paulo Shakarian |
Abstract | Pathogenic social media accounts such as terrorist supporters exploit communities of supporters for conducting attacks on social media. Early detection of PSM accounts is crucial as they are likely to be key users in making a harmful message “viral”. This paper overviews my recent doctoral work on utilizing causal inference to identify PSM accounts within a short time frame around their activity. The proposed scheme (1) assigns time-decay causality scores to users, (2) applies a community detection-based algorithm to group of users sharing similar causality scores and finally (3) deploys a classification algorithm to classify accounts. Unlike existing techniques that require network structure, cascade path, or content, our scheme relies solely on action log of users. |
Tasks | Causal Inference, Community Detection |
Published | 2018-06-26 |
URL | http://arxiv.org/abs/1806.09787v2 |
http://arxiv.org/pdf/1806.09787v2.pdf | |
PWC | https://paperswithcode.com/paper/causal-inference-for-early-detection-of |
Repo | |
Framework | |
Dental pathology detection in 3D cone-beam CT
Title | Dental pathology detection in 3D cone-beam CT |
Authors | Adel Zakirov, Matvey Ezhov, Maxim Gusarev, Vladimir Alexandrovsky, Evgeny Shumilov |
Abstract | Cone-beam computed tomography (CBCT) is a valuable imaging method in dental diagnostics that provides information not available in traditional 2D imaging. However, interpretation of CBCT images is a time-consuming process that requires a physician to work with complicated software. In this work we propose an automated pipeline composed of several deep convolutional neural networks and algorithmic heuristics. Our task is two-fold: a) find locations of each present tooth inside a 3D image volume, and b) detect several common tooth conditions in each tooth. The proposed system achieves 96.3% accuracy in tooth localization and an average of 0.94 AUROC for 6 common tooth conditions. |
Tasks | |
Published | 2018-10-24 |
URL | http://arxiv.org/abs/1810.10309v1 |
http://arxiv.org/pdf/1810.10309v1.pdf | |
PWC | https://paperswithcode.com/paper/dental-pathology-detection-in-3d-cone-beam-ct |
Repo | |
Framework | |
Neural Cross-Lingual Coreference Resolution and its Application to Entity Linking
Title | Neural Cross-Lingual Coreference Resolution and its Application to Entity Linking |
Authors | Gourab Kundu, Avirup Sil, Radu Florian, Wael Hamza |
Abstract | We propose an entity-centric neural cross-lingual coreference model that builds on multi-lingual embeddings and language-independent features. We perform both intrinsic and extrinsic evaluations of our model. In the intrinsic evaluation, we show that our model, when trained on English and tested on Chinese and Spanish, achieves competitive results to the models trained directly on Chinese and Spanish respectively. In the extrinsic evaluation, we show that our English model helps achieve superior entity linking accuracy on Chinese and Spanish test sets than the top 2015 TAC system without using any annotated data from Chinese or Spanish. |
Tasks | Coreference Resolution, Entity Linking |
Published | 2018-06-26 |
URL | http://arxiv.org/abs/1806.10201v1 |
http://arxiv.org/pdf/1806.10201v1.pdf | |
PWC | https://paperswithcode.com/paper/neural-cross-lingual-coreference-resolution |
Repo | |
Framework | |
A Pretrained DenseNet Encoder for Brain Tumor Segmentation
Title | A Pretrained DenseNet Encoder for Brain Tumor Segmentation |
Authors | Jean Stawiaski |
Abstract | This article presents a convolutional neural network for the automatic segmentation of brain tumors in multimodal 3D MR images based on a U-net architecture.We evaluate the use of a densely connected convolutional network encoder (DenseNet) which was pretrained on the ImageNet data set. We detail two network architectures that can take into account multiple 3D images as inputs. This work aims to identify if a generic pretrained network can be used for very specific medical applications where the target data differ both in the number of spatial dimensions as well as in the number of inputs channels. Moreover in order to regularize this transfer learning task we only train the decoder part of the U-net architecture. We evaluate the effectiveness of the proposed approach on the BRATS 2018 segmentation challenge where we obtained dice scores of 0.79, 0.90, 0.85 and 95/% Hausdorff distance of 2.9mm, 3.95mm, and 6.48mm for enhanced tumor core, whole tumor and tumor core respectively on the validation set. This scores degrades to 0.77, 0.88, 0.78 and 95 /% Hausdorff distance of 3.6mm, 5.72mm, and 5.83mm on the testing set. |
Tasks | Brain Tumor Segmentation, Transfer Learning |
Published | 2018-11-19 |
URL | http://arxiv.org/abs/1811.07542v1 |
http://arxiv.org/pdf/1811.07542v1.pdf | |
PWC | https://paperswithcode.com/paper/a-pretrained-densenet-encoder-for-brain-tumor |
Repo | |
Framework | |
Real-time Prediction of Segmentation Quality
Title | Real-time Prediction of Segmentation Quality |
Authors | Robert Robinson, Ozan Oktay, Wenjia Bai, Vanya Valindria, Mihir Sanghvi, Nay Aung, José Paiva, Filip Zemrak, Kenneth Fung, Elena Lukaschuk, Aaron Lee, Valentina Carapella, Young Jin Kim, Bernhard Kainz, Stefan Piechnik, Stefan Neubauer, Steffen Petersen, Chris Page, Daniel Rueckert, Ben Glocker |
Abstract | Recent advances in deep learning based image segmentation methods have enabled real-time performance with human-level accuracy. However, occasionally even the best method fails due to low image quality, artifacts or unexpected behaviour of black box algorithms. Being able to predict segmentation quality in the absence of ground truth is of paramount importance in clinical practice, but also in large-scale studies to avoid the inclusion of invalid data in subsequent analysis. In this work, we propose two approaches of real-time automated quality control for cardiovascular MR segmentations using deep learning. First, we train a neural network on 12,880 samples to predict Dice Similarity Coefficients (DSC) on a per-case basis. We report a mean average error (MAE) of 0.03 on 1,610 test samples and 97% binary classification accuracy for separating low and high quality segmentations. Secondly, in the scenario where no manually annotated data is available, we train a network to predict DSC scores from estimated quality obtained via a reverse testing strategy. We report an MAE=0.14 and 91% binary classification accuracy for this case. Predictions are obtained in real-time which, when combined with real-time segmentation methods, enables instant feedback on whether an acquired scan is analysable while the patient is still in the scanner. This further enables new applications of optimising image acquisition towards best possible analysis results. |
Tasks | Semantic Segmentation |
Published | 2018-06-16 |
URL | http://arxiv.org/abs/1806.06244v1 |
http://arxiv.org/pdf/1806.06244v1.pdf | |
PWC | https://paperswithcode.com/paper/real-time-prediction-of-segmentation-quality |
Repo | |
Framework | |
Demonstrating PAR4SEM - A Semantic Writing Aid with Adaptive Paraphrasing
Title | Demonstrating PAR4SEM - A Semantic Writing Aid with Adaptive Paraphrasing |
Authors | Seid Muhie Yimam, Chris Biemann |
Abstract | In this paper, we present Par4Sem, a semantic writing aid tool based on adaptive paraphrasing. Unlike many annotation tools that are primarily used to collect training examples, Par4Sem is integrated into a real word application, in this case a writing aid tool, in order to collect training examples from usage data. Par4Sem is a tool, which supports an adaptive, iterative, and interactive process where the underlying machine learning models are updated for each iteration using new training examples from usage data. After motivating the use of ever-learning tools in NLP applications, we evaluate Par4Sem by adopting it to a text simplification task through mere usage. |
Tasks | Text Simplification |
Published | 2018-08-21 |
URL | http://arxiv.org/abs/1808.06853v1 |
http://arxiv.org/pdf/1808.06853v1.pdf | |
PWC | https://paperswithcode.com/paper/demonstrating-par4sem-a-semantic-writing-aid |
Repo | |
Framework | |
Phenotype Inference with Semi-Supervised Mixed Membership Models
Title | Phenotype Inference with Semi-Supervised Mixed Membership Models |
Authors | Victor Rodriguez, Adler Perotte |
Abstract | Disease phenotyping algorithms process observational clinical data to identify patients with specific diseases. Supervised phenotyping methods require significant quantities of expert-labeled data, while unsupervised methods may learn non-disease phenotypes. To address these limitations, we propose the Semi-Supervised Mixed Membership Model (SS3M) – a probabilistic graphical model for learning disease phenotypes from clinical data with relatively few labels. We show SS3M can learn interpretable, disease-specific phenotypes which capture the clinical characteristics of the diseases specified by the labels provided. |
Tasks | |
Published | 2018-12-07 |
URL | http://arxiv.org/abs/1812.03222v2 |
http://arxiv.org/pdf/1812.03222v2.pdf | |
PWC | https://paperswithcode.com/paper/phenotype-inference-with-semi-supervised |
Repo | |
Framework | |