January 28, 2020

3037 words 15 mins read

Paper Group ANR 808

It could be worse, it could be raining: reliable automatic meteorological forecasting. Optimal Learning of Mallows Block Model. Deep Learning for Vertex Reconstruction of Neutrino-Nucleus Interaction Events with Combined Energy and Time Data. Predicted disease compositions of human gliomas estimated from multiparametric MRI can predict endothelial …

It could be worse, it could be raining: reliable automatic meteorological forecasting


Title	It could be worse, it could be raining: reliable automatic meteorological forecasting
Authors	Matteo Cristani, Francesco Domenichini, Claudio Tomazzoli, Luca Viganò, Margherita Zorzi
Abstract	Meteorological forecasting provides reliable prediction about the future weather within a given interval of time. Meteorological forecasting can be viewed as a form of hybrid diagnostic reasoning and can be mapped onto an integrated conceptual framework. The automation of the forecasting process would be helpful in a number of contexts, in particular: when the amount of data is too wide to be dealt with manually; to support forecasters education; when forecasting about underpopulated geographic areas is not interesting for everyday life (and then is out from human forecasters’ tasks) but is central for tourism sponsorship. We present logic MeteoLOG, a framework that models the main steps of the reasoner the forecaster adopts to provide a bulletin. MeteoLOG rests on several traditions, mainly on fuzzy, temporal and probabilistic logics. On this basis, we also introduce the algorithm Tournament, that transforms a set of MeteoLOG rules into a defeasible theory, that can be implemented into an automatic reasoner. We finally propose an example that models a real world forecasting scenario.
Tasks
Published	2019-01-28
URL	http://arxiv.org/abs/1901.09867v2
PDF	http://arxiv.org/pdf/1901.09867v2.pdf
PWC	https://paperswithcode.com/paper/it-could-be-worse-it-could-be-raining
Repo
Framework

Optimal Learning of Mallows Block Model


Title	Optimal Learning of Mallows Block Model
Authors	Róbert Busa-Fekete, Dimitris Fotakis, Balázs Szörényi, Manolis Zampetakis
Abstract	The Mallows model, introduced in the seminal paper of Mallows 1957, is one of the most fundamental ranking distribution over the symmetric group $S_m$. To analyze more complex ranking data, several studies considered the Generalized Mallows model defined by Fligner and Verducci 1986. Despite the significant research interest of ranking distributions, the exact sample complexity of estimating the parameters of a Mallows and a Generalized Mallows Model is not well-understood. The main result of the paper is a tight sample complexity bound for learning Mallows and Generalized Mallows Model. We approach the learning problem by analyzing a more general model which interpolates between the single parameter Mallows Model and the $m$ parameter Mallows model. We call our model Mallows Block Model – referring to the Block Models that are a popular model in theoretical statistics. Our sample complexity analysis gives tight bound for learning the Mallows Block Model for any number of blocks. We provide essentially matching lower bounds for our sample complexity results. As a corollary of our analysis, it turns out that, if the central ranking is known, one single sample from the Mallows Block Model is sufficient to estimate the spread parameters with error that goes to zero as the size of the permutations goes to infinity. In addition, we calculate the exact rate of the parameter estimation error.
Tasks
Published	2019-06-03
URL	https://arxiv.org/abs/1906.01009v1
PDF	https://arxiv.org/pdf/1906.01009v1.pdf
PWC	https://paperswithcode.com/paper/optimal-learning-of-mallows-block-model
Repo
Framework

Deep Learning for Vertex Reconstruction of Neutrino-Nucleus Interaction Events with Combined Energy and Time Data


Title	Deep Learning for Vertex Reconstruction of Neutrino-Nucleus Interaction Events with Combined Energy and Time Data
Authors	Linghao Song, Fan Chen, Steven R. Young, Catherine D. Schuman, Gabriel Perdue, Thomas E. Potok
Abstract	We present a deep learning approach for vertex reconstruction of neutrino-nucleus interaction events, a problem in the domain of high energy physics. In this approach, we combine both energy and timing data that are collected in the MINERvA detector to perform classification and regression tasks. We show that the resulting network achieves higher accuracy than previous results while requiring a smaller model size and less training time. In particular, the proposed model outperforms the state-of-the-art by 4.00% on classification accuracy. For the regression task, our model achieves 0.9919 on the coefficient of determination, higher than the previous work (0.96).
Tasks
Published	2019-02-02
URL	http://arxiv.org/abs/1902.00743v1
PDF	http://arxiv.org/pdf/1902.00743v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-vertex-reconstruction-of
Repo
Framework

Predicted disease compositions of human gliomas estimated from multiparametric MRI can predict endothelial proliferation, tumor grade, and overall survival


Title	Predicted disease compositions of human gliomas estimated from multiparametric MRI can predict endothelial proliferation, tumor grade, and overall survival
Authors	Emily E Diller, Sha Cao, Beth Ey, Robert Lober, Jason G Parker
Abstract	Background and Purpose: Biopsy is the main determinants of glioma clinical management, but require invasive sampling that fail to detect relevant features because of tumor heterogeneity. The purpose of this study was to evaluate the accuracy of a voxel-wise, multiparametric MRI radiomic method to predict features and develop a minimally invasive method to objectively assess neoplasms. Methods: Multiparametric MRI were registered to T1-weighted gadolinium contrast-enhanced data using a 12 degree-of-freedom affine model. The retrospectively collected MRI data included T1-weighted, T1-weighted gadolinium contrast-enhanced, T2-weighted, fluid attenuated inversion recovery, and multi-b-value diffusion-weighted acquired at 1.5T or 3.0T. Clinical experts provided voxel-wise annotations for five disease states on a subset of patients to establish a training feature vector of 611,930 observations. Then, a k-nearest-neighbor (k-NN) classifier was trained using a 25% hold-out design. The trained k-NN model was applied to 13,018,171 observations from seventeen histologically confirmed glioma patients. Linear regression tested overall survival (OS) relationship to predicted disease compositions (PDC) and diagnostic age (alpha = 0.05). Canonical discriminant analysis tested if PDC and diagnostic age could differentiate clinical, genetic, and microscopic factors (alpha = 0.05). Results: The model predicted voxel annotation class with a Dice similarity coefficient of 94.34% +/- 2.98. Linear combinations of PDCs and diagnostic age predicted OS (p = 0.008), grade (p = 0.014), and endothelia proliferation (p = 0.003); but fell short predicting gene mutations for TP53BP1 and IDH1. Conclusions: This voxel-wise, multi-parametric MRI radiomic strategy holds potential as a non-invasive decision-making aid for clinicians managing patients with glioma.
Tasks	Decision Making
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02334v1
PDF	https://arxiv.org/pdf/1908.02334v1.pdf
PWC	https://paperswithcode.com/paper/predicted-disease-compositions-of-human
Repo
Framework

HyperCon: Image-To-Video Model Transfer for Video-To-Video Translation Tasks


Title	HyperCon: Image-To-Video Model Transfer for Video-To-Video Translation Tasks
Authors	Ryan Szeto, Mostafa El-Khamy, Jungwon Lee, Jason J. Corso
Abstract	Video-to-video translation for super-resolution, inpainting, style transfer, etc. is more difficult than corresponding image-to-image translation tasks due to the temporal consistency problem that, if left unaddressed, results in distracting flickering effects. Although video models designed from scratch produce temporally consistent results, training them to match the vast visual knowledge captured by image models requires an intractable number of videos. To combine the benefits of image and video models, we propose an image-to-video model transfer method called Hyperconsistency (HyperCon) that transforms any well-trained image model into a temporally consistent video model without fine-tuning. HyperCon works by translating a synthetic temporally interpolated video frame-wise and then aggregating over temporally localized windows on the interpolated video. It handles both masked and unmasked inputs, enabling support for even more video-to-video tasks than prior image-to-video model transfer techniques. We demonstrate HyperCon on video style transfer and inpainting, where it performs favorably compared to prior state-of-the-art video consistency and video inpainting methods, all without training on a single stylized or incomplete video.
Tasks	Image-to-Image Translation, Style Transfer, Super-Resolution, Video Inpainting, Video Style Transfer
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04950v1
PDF	https://arxiv.org/pdf/1912.04950v1.pdf
PWC	https://paperswithcode.com/paper/hypercon-image-to-video-model-transfer-for
Repo
Framework

Generalization in Generation: A closer look at Exposure Bias


Title	Generalization in Generation: A closer look at Exposure Bias
Authors	Florian Schmidt
Abstract	Exposure bias refers to the train-test discrepancy that seemingly arises when an autoregressive generative model uses only ground-truth contexts at training time but generated ones at test time. We separate the contributions of the model and the learning framework to clarify the debate on consequences and review proposed counter-measures. In this light, we argue that generalization is the underlying property to address and propose unconditional generation as its fundamental benchmark. Finally, we combine latent variable modeling with a recent formulation of exploration in reinforcement learning to obtain a rigorous handling of true and generated contexts. Results on language modeling and variational sentence auto-encoding confirm the model’s generalization capability.
Tasks	Language Modelling
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00292v2
PDF	https://arxiv.org/pdf/1910.00292v2.pdf
PWC	https://paperswithcode.com/paper/generalization-in-generation-a-closer-look-at
Repo
Framework

Scaling up deep neural networks: a capacity allocation perspective


Title	Scaling up deep neural networks: a capacity allocation perspective
Authors	Jonathan Donier
Abstract	Following the recent work on capacity allocation, we formulate the conjecture that the shattering problem in deep neural networks can only be avoided if the capacity propagation through layers has a non-degenerate continuous limit when the number of layers tends to infinity. This allows us to study a number of commonly used architectures and determine which scaling relations should be enforced in practice as the number of layers grows large. In particular, we recover the conditions of Xavier initialization in the multi-channel case, and we find that weights and biases should be scaled down as the inverse square root of the number of layers for deep residual networks and as the inverse square root of the desired memory length for recurrent networks.
Tasks
Published	2019-03-11
URL	http://arxiv.org/abs/1903.04455v2
PDF	http://arxiv.org/pdf/1903.04455v2.pdf
PWC	https://paperswithcode.com/paper/scaling-up-deep-neural-networks-a-capacity
Repo
Framework

Improving Mechanical Ventilator Clinical Decision Support Systems with A Machine Learning Classifier for Determining Ventilator Mode


Title	Improving Mechanical Ventilator Clinical Decision Support Systems with A Machine Learning Classifier for Determining Ventilator Mode
Authors	Gregory B. Rehm, Brooks T. Kuhn, Jimmy Nguyen, Nicholas R. Anderson, Chen-Nee Chuah, Jason Y. Adams
Abstract	Clinical decision support systems (CDSS) will play an in-creasing role in improving the quality of medical care for critically ill patients. However, due to limitations in current informatics infrastructure, CDSS do not always have com-plete information on state of supporting physiologic monitor-ing devices, which can limit the input data available to CDSS. This is especially true in the use case of mechanical ventilation (MV), where current CDSS have no knowledge of critical ventilation settings, such as ventilation mode. To enable MV CDSS to make accurate recommendations related to ventilator mode, we developed a highly performant ma-chine learning model that is able to perform per-breath clas-sification of 5 of the most widely used ventilation modes in the USA with an average F1-score of 97.52%. We also show how our approach makes methodologic improvements over previous work and that it is highly robust to missing data caused by software/sensor error.
Tasks
Published	2019-04-29
URL	http://arxiv.org/abs/1904.12969v1
PDF	http://arxiv.org/pdf/1904.12969v1.pdf
PWC	https://paperswithcode.com/paper/improving-mechanical-ventilator-clinical
Repo
Framework

Compressed Sensing with Probability-based Prior Information


Title	Compressed Sensing with Probability-based Prior Information
Authors	Q. Jiang, S. Li, Z. Zhu, H. Bai, X. He, R. C. de Lamare
Abstract	This paper deals with the design of a sensing matrix along with a sparse recovery algorithm by utilizing the probability-based prior information for compressed sensing system. With the knowledge of the probability for each atom of the dictionary being used, a diagonal weighted matrix is obtained and then the sensing matrix is designed by minimizing a weighted function such that the Gram of the equivalent dictionary is as close to the Gram of dictionary as possible. An analytical solution for the corresponding sensing matrix is derived which leads to low computational complexity. We also exploit this prior information through the sparse recovery stage and propose a probability-driven orthogonal matching pursuit algorithm that improves the accuracy of the recovery. Simulations for synthetic data and application scenarios of surveillance video are carried out to compare the performance of the proposed methods with some existing algorithms. The results reveal that the proposed CS system outperforms existing CS systems.
Tasks
Published	2019-10-27
URL	https://arxiv.org/abs/1910.12258v1
PDF	https://arxiv.org/pdf/1910.12258v1.pdf
PWC	https://paperswithcode.com/paper/compressed-sensing-with-probability-based
Repo
Framework

Supply-Power-Constrained Cable Capacity Maximization Using Deep Neural Networks


Title	Supply-Power-Constrained Cable Capacity Maximization Using Deep Neural Networks
Authors	Junho Cho, Sethumadhavan Chandrasekhar, Erixhen Sula, Samuel Olsson, Ellsworth Burrows, Greg Raybon, Roland Ryf, Nicolas Fontaine, Jean-Christophe Antona, Steve Grubb, Peter Winzer, Andrew Chraplyvy
Abstract	We experimentally achieve a 19% capacity gain per Watt of electrical supply power in a 12-span link by eliminating gain flattening filters and optimizing launch powers using machine learning by deep neural networks in a massively parallel fiber context.
Tasks
Published	2019-10-02
URL	https://arxiv.org/abs/1910.02050v1
PDF	https://arxiv.org/pdf/1910.02050v1.pdf
PWC	https://paperswithcode.com/paper/supply-power-constrained-cable-capacity
Repo
Framework

LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices


Title	LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices
Authors	Radu Alexandru Rosu, Peer Schütt, Jan Quenzel, Sven Behnke
Abstract	Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. However, applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of structured data. Here, we propose LatticeNet, a novel approach for 3D semantic segmentation, which takes as input raw point clouds. A PointNet describes the local geometry which we embed into a sparse permutohedral lattice. The lattice allows for fast convolutions while keeping a low memory footprint. Further, we introduce DeformSlice, a novel learned data-dependent interpolation for projecting lattice features back onto the point cloud. We present results of 3D segmentation on various datasets where our method achieves state-of-the-art performance.
Tasks	3D Semantic Segmentation, Semantic Segmentation
Published	2019-12-12
URL	https://arxiv.org/abs/1912.05905v1
PDF	https://arxiv.org/pdf/1912.05905v1.pdf
PWC	https://paperswithcode.com/paper/latticenet-fast-point-cloud-segmentation
Repo
Framework

Lower Bounds for Adversarially Robust PAC Learning


Title	Lower Bounds for Adversarially Robust PAC Learning
Authors	Dimitrios I. Diochnos, Saeed Mahloujifar, Mohammad Mahmoody
Abstract	In this work, we initiate a formal study of probably approximately correct (PAC) learning under evasion attacks, where the adversary’s goal is to \emph{misclassify} the adversarially perturbed sample point $\widetilde{x}$, i.e., $h(\widetilde{x})\neq c(\widetilde{x})$, where $c$ is the ground truth concept and $h$ is the learned hypothesis. Previous work on PAC learning of adversarial examples have all modeled adversarial examples as corrupted inputs in which the goal of the adversary is to achieve $h(\widetilde{x}) \neq c(x)$, where $x$ is the original untampered instance. These two definitions of adversarial risk coincide for many natural distributions, such as images, but are incomparable in general. We first prove that for many theoretically natural input spaces of high dimension $n$ (e.g., isotropic Gaussian in dimension $n$ under $\ell_2$ perturbations), if the adversary is allowed to apply up to a sublinear $o(x)$ amount of perturbations on the test instances, PAC learning requires sample complexity that is exponential in $n$. This is in contrast with results proved using the corrupted-input framework, in which the sample complexity of robust learning is only polynomially more. We then formalize hybrid attacks in which the evasion attack is preceded by a poisoning attack. This is perhaps reminiscent of “trapdoor attacks” in which a poisoning phase is involved as well, but the evasion phase here uses the error-region definition of risk that aims at misclassifying the perturbed instances. In this case, we show PAC learning is sometimes impossible all together, even when it is possible without the attack (e.g., due to the bounded VC dimension).
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05815v1
PDF	https://arxiv.org/pdf/1906.05815v1.pdf
PWC	https://paperswithcode.com/paper/lower-bounds-for-adversarially-robust-pac
Repo
Framework

Building an Affordances Map with Interactive Perception


Title	Building an Affordances Map with Interactive Perception
Authors	Leni K. Le Goff, Oussama Yaakoubi, Alexandre Coninx, Stephane Doncieux
Abstract	Robots need to understand their environment to perform their task. If it is possible to pre-program a visual scene analysis process in closed environments, robots operating in an open environment would benefit from the ability to learn it through their interaction with their environment. This ability furthermore opens the way to the acquisition of affordances maps in which the action capabilities of the robot structure its visual scene understanding. We propose an approach to build such affordances maps by relying on an interactive perception approach and an online classification. In the proposed formalization of affordances, actions and effects are related to visual features, not objects, and they can be combined. We have tested the approach on three action primitives and on a real PR2 robot.
Tasks	Scene Understanding
Published	2019-03-11
URL	http://arxiv.org/abs/1903.04413v1
PDF	http://arxiv.org/pdf/1903.04413v1.pdf
PWC	https://paperswithcode.com/paper/building-an-affordances-map-with-interactive
Repo
Framework

Uncertainty Quantification in Computer-Aided Diagnosis: Make Your Model say “I don’t know” for Ambiguous Cases


Title	Uncertainty Quantification in Computer-Aided Diagnosis: Make Your Model say “I don’t know” for Ambiguous Cases
Authors	Max-Heinrich Laves, Sontje Ihler, Tobias Ortmaier
Abstract	We evaluate two different methods for the integration of prediction uncertainty into diagnostic image classifiers to increase patient safety in deep learning. In the first method, Monte Carlo sampling is applied with dropout at test time to get a posterior distribution of the class labels (Bayesian ResNet). The second method extends ResNet to a probabilistic approach by predicting the parameters of the posterior distribution and sampling the final result from it (Variational ResNet).The variance of the posterior is used as metric for uncertainty.Both methods are trained on a data set of optical coherence tomography scans showing four different retinal conditions. Our results shown that cases in which the classifier predicts incorrectly correlate with a higher uncertainty. Mean uncertainty of incorrectly diagnosed cases was between 4.6 and 8.1 times higher than mean uncertainty of correctly diagnosed cases. Modeling of the prediction uncertainty in computer-aided diagnosis with deep learning yields more reliable results and is anticipated to increase patient safety.
Tasks
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00792v1
PDF	https://arxiv.org/pdf/1908.00792v1.pdf
PWC	https://paperswithcode.com/paper/uncertainty-quantification-in-computer-aided
Repo
Framework

FineText: Text Classification via Attention-based Language Model Fine-tuning


Title	FineText: Text Classification via Attention-based Language Model Fine-tuning
Authors	Yunzhe Tao, Saurabh Gupta, Satyapriya Krishna, Xiong Zhou, Orchid Majumder, Vineet Khare
Abstract	Training deep neural networks from scratch on natural language processing (NLP) tasks requires significant amount of manually labeled text corpus and substantial time to converge, which usually cannot be satisfied by the customers. In this paper, we aim to develop an effective transfer learning algorithm by fine-tuning a pre-trained language model. The goal is to provide expressive and convenient-to-use feature extractors for downstream NLP tasks, and achieve improvement in terms of accuracy, data efficiency, and generalization to new domains. Therefore, we propose an attention-based fine-tuning algorithm that automatically selects relevant contextualized features from the pre-trained language model and uses those features on downstream text classification tasks. We test our methods on six widely-used benchmarking datasets, and achieve new state-of-the-art performance on all of them. Moreover, we then introduce an alternative multi-task learning approach, which is an end-to-end algorithm given the pre-trained model. By doing multi-task learning, one can largely reduce the total training time by trading off some classification accuracy.
Tasks	Language Modelling, Multi-Task Learning, Text Classification, Transfer Learning
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11959v1
PDF	https://arxiv.org/pdf/1910.11959v1.pdf
PWC	https://paperswithcode.com/paper/finetext-text-classification-via-attention
Repo
Framework