October 18, 2019

2962 words 14 mins read

Paper Group ANR 466

Average Size of Implicational Bases. Generating Synthetic but Plausible Healthcare Record Datasets. ClickBAIT-v2: Training an Object Detector in Real-Time. Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning. On Deep Neural Networks for Detecting Heart Disease. Brain-inspired photonic signal processor for periodic pattern generation …

Average Size of Implicational Bases


Title	Average Size of Implicational Bases
Authors	Giacomo Kahn, Alexandre Bazin
Abstract	Implicational bases are objects of interest in formal concept analysis and its applications. Unfortunately, even the smallest base, the Duquenne-Guigues base, has an exponential size in the worst case. In this paper, we use results on the average number of minimal transversals in random hypergraphs to show that the base of proper premises is, on average, of quasi-polynomial size.
Tasks
Published	2018-02-12
URL	http://arxiv.org/abs/1802.04032v1
PDF	http://arxiv.org/pdf/1802.04032v1.pdf
PWC	https://paperswithcode.com/paper/average-size-of-implicational-bases
Repo
Framework

Generating Synthetic but Plausible Healthcare Record Datasets


Title	Generating Synthetic but Plausible Healthcare Record Datasets
Authors	Laura Aviñó, Matteo Ruffini, Ricard Gavaldà
Abstract	Generating datasets that “look like” given real ones is an interesting tasks for healthcare applications of ML and many other fields of science and engineering. In this paper we propose a new method of general application to binary datasets based on a method for learning the parameters of a latent variable moment that we have previously used for clustering patient datasets. We compare our method with a recent proposal (MedGan) based on generative adversarial methods and find that the synthetic datasets we generate are globally more realistic in at least two senses: real and synthetic instances are harder to tell apart by Random Forests, and the MMD statistic. The most likely explanation is that our method does not suffer from the “mode collapse” which is an admitted problem of GANs. Additionally, the generative models we generate are easy to interpret, unlike the rather obscure GANs. Our experiments are performed on two patient datasets containing ICD-9 diagnostic codes: the publicly available MIMIC-III dataset and a dataset containing admissions for congestive heart failure during 7 years at Hospital de Sant Pau in Barcelona.
Tasks
Published	2018-07-04
URL	http://arxiv.org/abs/1807.01514v1
PDF	http://arxiv.org/pdf/1807.01514v1.pdf
PWC	https://paperswithcode.com/paper/generating-synthetic-but-plausible-healthcare
Repo
Framework

ClickBAIT-v2: Training an Object Detector in Real-Time


Title	ClickBAIT-v2: Training an Object Detector in Real-Time
Authors	Ervin Teng, Rui Huang, Bob Iannucci
Abstract	Modern deep convolutional neural networks (CNNs) for image classification and object detection are often trained offline on large static datasets. Some applications, however, will require training in real-time on live video streams with a human-in-the-loop. We refer to this class of problem as time-ordered online training (ToOT). These problems will require a consideration of not only the quantity of incoming training data, but the human effort required to annotate and use it. We demonstrate and evaluate a system tailored to training an object detector on a live video stream with minimal input from a human operator. We show that we can obtain bounding box annotation from weakly-supervised single-point clicks through interactive segmentation. Furthermore, by exploiting the time-ordered nature of the video stream through object tracking, we can increase the average training benefit of human interactions by 3-4 times.
Tasks	Image Classification, Interactive Segmentation, Object Detection, Object Tracking
Published	2018-03-27
URL	http://arxiv.org/abs/1803.10358v1
PDF	http://arxiv.org/pdf/1803.10358v1.pdf
PWC	https://paperswithcode.com/paper/clickbait-v2-training-an-object-detector-in
Repo
Framework

Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning


Title	Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
Authors	Jakob N. Foerster, Francis Song, Edward Hughes, Neil Burch, Iain Dunning, Shimon Whiteson, Matthew Botvinick, Michael Bowling
Abstract	When observing the actions of others, humans make inferences about why they acted as they did, and what this implies about the world; humans also use the fact that their actions will be interpreted in this manner, allowing them to act informatively and thereby communicate efficiently with others. Although learning algorithms have recently achieved superhuman performance in a number of two-player, zero-sum games, scalable multi-agent reinforcement learning algorithms that can discover effective strategies and conventions in complex, partially observable settings have proven elusive. We present the Bayesian action decoder (BAD), a new multi-agent learning method that uses an approximate Bayesian update to obtain a public belief that conditions on the actions taken by all agents in the environment. BAD introduces a new Markov decision process, the public belief MDP, in which the action space consists of all deterministic partial policies, and exploits the fact that an agent acting only on this public belief state can still learn to use its private information if the action space is augmented to be over all partial policies mapping private information into environment actions. The Bayesian update is closely related to the theory of mind reasoning that humans carry out when observing others’ actions. We first validate BAD on a proof-of-principle two-step matrix game, where it outperforms policy gradient methods; we then evaluate BAD on the challenging, cooperative partial-information card game Hanabi, where, in the two-player setting, it surpasses all previously published learning and hand-coded approaches, establishing a new state of the art.
Tasks	Multi-agent Reinforcement Learning, Policy Gradient Methods
Published	2018-11-04
URL	https://arxiv.org/abs/1811.01458v3
PDF	https://arxiv.org/pdf/1811.01458v3.pdf
PWC	https://paperswithcode.com/paper/bayesian-action-decoder-for-deep-multi-agent
Repo
Framework

On Deep Neural Networks for Detecting Heart Disease


Title	On Deep Neural Networks for Detecting Heart Disease
Authors	Nathalie-Sofia Tomov, Stanimire Tomov
Abstract	Heart disease is the leading cause of death, and experts estimate that approximately half of all heart attacks and strokes occur in people who have not been flagged as “at risk.” Thus, there is an urgent need to improve the accuracy of heart disease diagnosis. To this end, we investigate the potential of using data analysis, and in particular the design and use of deep neural networks (DNNs) for detecting heart disease based on routine clinical data. Our main contribution is the design, evaluation, and optimization of DNN architectures of increasing depth for heart disease diagnosis. This work led to the discovery of a novel five layer DNN architecture - named Heart Evaluation for Algorithmic Risk-reduction and Optimization Five (HEARO-5) – that yields best prediction accuracy. HEARO-5’s design employs regularization optimization and automatically deals with missing data and/or data outliers. To evaluate and tune the architectures we use k-way cross-validation as well as Matthews correlation coefficient (MCC) to measure the quality of our classifications. The study is performed on the publicly available Cleveland dataset of medical information, and we are making our developments open source, to further facilitate openness and research on the use of DNNs in medicine. The HEARO-5 architecture, yielding 99% accuracy and 0.98 MCC, significantly outperforms currently published research in the area.
Tasks
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07168v1
PDF	http://arxiv.org/pdf/1808.07168v1.pdf
PWC	https://paperswithcode.com/paper/on-deep-neural-networks-for-detecting-heart
Repo
Framework

Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation


Title	Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation
Authors	Piotr Antonik, Marc Haelterman, Serge Massar
Abstract	Reservoir computing is a bio-inspired computing paradigm for processing time-dependent signals. Its hardware implementations have received much attention because of their simplicity and remarkable performance on a series of benchmark tasks. In previous experiments the output was uncoupled from the system and in most cases simply computed offline on a post-processing computer. However, numerical investigations have shown that feeding the output back into the reservoir would open the possibility of long-horizon time series forecasting. Here we present a photonic reservoir computer with output feedback, and demonstrate its capacity to generate periodic time series and to emulate chaotic systems. We study in detail the effect of experimental noise on system performance. In the case of chaotic systems, this leads us to introduce several metrics, based on standard signal processing techniques, to evaluate the quality of the emulation. Our work significantly enlarges the range of tasks that can be solved by hardware reservoir computers, and therefore the range of applications they could potentially tackle. It also raises novel questions in nonlinear dynamics and chaos theory.
Tasks	Time Series, Time Series Forecasting
Published	2018-02-06
URL	http://arxiv.org/abs/1802.02026v1
PDF	http://arxiv.org/pdf/1802.02026v1.pdf
PWC	https://paperswithcode.com/paper/brain-inspired-photonic-signal-processor-for
Repo
Framework

ESCaF: Pupil Centre Localization Algorithm with Candidate Filtering


Title	ESCaF: Pupil Centre Localization Algorithm with Candidate Filtering
Authors	Anjith George, Aurobinda Routray
Abstract	Algorithms for accurate localization of pupil centre is essential for gaze tracking in real world conditions. Most of the algorithms fail in real world conditions like illumination variations, contact lenses, glasses, eye makeup, motion blur, noise, etc. We propose a new algorithm which improves the detection rate in real world conditions. The proposed algorithm uses both edges as well as intensity information along with a candidate filtering approach to identify the best pupil candidate. A simple tracking scheme has also been added which improves the processing speed. The algorithm has been evaluated in Labelled Pupil in the Wild (LPW) dataset, largest in its class which contains real world conditions. The proposed algorithm outperformed the state of the art algorithms while achieving real-time performance.
Tasks
Published	2018-07-27
URL	http://arxiv.org/abs/1807.10520v1
PDF	http://arxiv.org/pdf/1807.10520v1.pdf
PWC	https://paperswithcode.com/paper/escaf-pupil-centre-localization-algorithm
Repo
Framework

On the influence of Dice loss function in multi-class organ segmentation of abdominal CT using 3D fully convolutional networks


Title	On the influence of Dice loss function in multi-class organ segmentation of abdominal CT using 3D fully convolutional networks
Authors	Chen Shen, Holger R. Roth, Hirohisa Oda, Masahiro Oda, Yuichiro Hayashi, Kazunari Misawa, Kensaku Mori
Abstract	Deep learning-based methods achieved impressive results for the segmentation of medical images. With the development of 3D fully convolutional networks (FCNs), it has become feasible to produce improved results for multi-organ segmentation of 3D computed tomography (CT) images. The results of multi-organ segmentation using deep learning-based methods not only depend on the choice of networks architecture, but also strongly rely on the choice of loss function. In this paper, we present a discussion on the influence of Dice-based loss functions for multi-class organ segmentation using a dataset of abdominal CT volumes. We investigated three different types of weighting the Dice loss functions based on class label frequencies (uniform, simple and square) and evaluate their influence on segmentation accuracies. Furthermore, we compared the influence of different initial learning rates. We achieved average Dice scores of 81.3%, 59.5% and 31.7% for uniform, simple and square types of weighting when the learning rate is 0.001, and 78.2%, 81.0% and 58.5% for each weighting when the learning rate is 0.01. Our experiments indicated a strong relationship between class balancing weights and initial learning rate in training.
Tasks	Computed Tomography (CT)
Published	2018-01-18
URL	http://arxiv.org/abs/1801.05912v1
PDF	http://arxiv.org/pdf/1801.05912v1.pdf
PWC	https://paperswithcode.com/paper/on-the-influence-of-dice-loss-function-in
Repo
Framework

Data-Efficient Weakly Supervised Learning for Low-Resource Audio Event Detection Using Deep Learning


Title	Data-Efficient Weakly Supervised Learning for Low-Resource Audio Event Detection Using Deep Learning
Authors	Veronica Morfi, Dan Stowell
Abstract	We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most datasets are “weakly labelled” having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose a data-efficient training of a stacked convolutional and recurrent neural network. This neural network is trained in a multi instance learning setting for which we introduce a new loss function that leads to improved training compared to the usual approaches for weakly supervised learning. We successfully test our approach on two low-resource datasets that lack temporal labels.
Tasks
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06972v2
PDF	http://arxiv.org/pdf/1807.06972v2.pdf
PWC	https://paperswithcode.com/paper/data-efficient-weakly-supervised-learning-for
Repo
Framework

Quantile Regression for Qualifying Match of GEFCom2017 Probabilistic Load Forecasting


Title	Quantile Regression for Qualifying Match of GEFCom2017 Probabilistic Load Forecasting
Authors	Florian Ziel
Abstract	We present a simple quantile regression-based forecasting method that was applied in a probabilistic load forecasting framework of the Global Energy Forecasting Competition 2017 (GEFCom2017). The hourly load data is log transformed and split into a long-term trend component and a remainder term. The key forecasting element is the quantile regression approach for the remainder term that takes into account weekly and annual seasonalities such as their interactions. Temperature information is only used to stabilize the forecast of the long-term trend component. Public holidays information is ignored. Still, the forecasting method placed second in the open data track and fourth in the definite data track with our forecasting method, which is remarkable given simplicity of the model. The method also outperforms the Vanilla benchmark consistently.
Tasks	Load Forecasting
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03561v1
PDF	http://arxiv.org/pdf/1809.03561v1.pdf
PWC	https://paperswithcode.com/paper/quantile-regression-for-qualifying-match-of
Repo
Framework

Deep Q learning for fooling neural networks


Title	Deep Q learning for fooling neural networks
Authors	Mandar Kulkarni
Abstract	Deep learning models are vulnerable to external attacks. In this paper, we propose a Reinforcement Learning (RL) based approach to generate adversarial examples for the pre-trained (target) models. We assume a semi black-box setting where the only access an adversary has to the target model is the class probabilities obtained for the input queries. We train a Deep Q Network (DQN) agent which, with experience, learns to attack only a small portion of image pixels to generate non-targeted adversarial images. Initially, an agent explores an environment by sequentially modifying random sets of image pixels and observes its effect on the class probabilities. At the end of an episode, it receives a positive (negative) reward if it succeeds (fails) to alter the label of the image. Experimental results with MNIST, CIFAR-10 and Imagenet datasets demonstrate that our RL framework is able to learn an effective attack policy.
Tasks	Q-Learning
Published	2018-11-13
URL	http://arxiv.org/abs/1811.05521v1
PDF	http://arxiv.org/pdf/1811.05521v1.pdf
PWC	https://paperswithcode.com/paper/deep-q-learning-for-fooling-neural-networks
Repo
Framework

Contextualized Non-local Neural Networks for Sequence Learning


Title	Contextualized Non-local Neural Networks for Sequence Learning
Authors	Pengfei Liu, Shuaichen Chang, Xuanjing Huang, Jian Tang, Jackie Chi Kit Cheung
Abstract	Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which self-attention, as exemplified by the Transformer model, and graph neural networks (GNNs) have attracted much attention. In this paper, we propose an approach that combines and draws on the complementary strengths of these two methods. Specifically, we propose contextualized non-local neural networks (CN$^{\textbf{3}}$), which can both dynamically construct a task-specific structure of a sentence and leverage rich local dependencies within a particular neighborhood. Experimental results on ten NLP tasks in text classification, semantic matching, and sequence labeling show that our proposed model outperforms competitive baselines and discovers task-specific dependency structures, thus providing better interpretability to users.
Tasks	Text Classification
Published	2018-11-21
URL	http://arxiv.org/abs/1811.08600v1
PDF	http://arxiv.org/pdf/1811.08600v1.pdf
PWC	https://paperswithcode.com/paper/contextualized-non-local-neural-networks-for
Repo
Framework

Deploying Deep Neural Networks in the Embedded Space


Title	Deploying Deep Neural Networks in the Embedded Space
Authors	Stylianos I. Venieris, Alexandros Kouris, Christos-Savvas Bouganis
Abstract	Recently, Deep Neural Networks (DNNs) have emerged as the dominant model across various AI applications. In the era of IoT and mobile systems, the efficient deployment of DNNs on embedded platforms is vital to enable the development of intelligent applications. This paper summarises our recent work on the optimised mapping of DNNs on embedded settings. By covering such diverse topics as DNN-to-accelerator toolflows, high-throughput cascaded classifiers and domain-specific model design, the presented set of works aim to enable the deployment of sophisticated deep learning models on cutting-edge mobile and embedded systems.
Tasks
Published	2018-06-22
URL	http://arxiv.org/abs/1806.08616v1
PDF	http://arxiv.org/pdf/1806.08616v1.pdf
PWC	https://paperswithcode.com/paper/deploying-deep-neural-networks-in-the
Repo
Framework

An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN


Title	An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN
Authors	Xi Mo, Ke Tao, Quan Wang, Guanghui Wang
Abstract	Polyp has long been considered as one of the major etiologies to colorectal cancer which is a fatal disease around the world, thus early detection and recognition of polyps plays a crucial role in clinical routines. Accurate diagnoses of polyps through endoscopes operated by physicians becomes a challenging task not only due to the varying expertise of physicians, but also the inherent nature of endoscopic inspections. To facilitate this process, computer-aid techniques that emphasize fully-conventional image processing and novel machine learning enhanced approaches have been dedicatedly designed for polyp detection in endoscopic videos or images. Among all proposed algorithms, deep learning based methods take the lead in terms of multiple metrics in evolutions for algorithmic performance. In this work, a highly effective model, namely the faster region-based convolutional neural network (Faster R-CNN) is implemented for polyp detection. In comparison with the reported results of the state-of-the-art approaches on polyps detection, extensive experiments demonstrate that the Faster R-CNN achieves very competing results, and it is an efficient approach for clinical practice.
Tasks
Published	2018-09-04
URL	http://arxiv.org/abs/1809.01263v1
PDF	http://arxiv.org/pdf/1809.01263v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-approach-for-polyps-detection-in
Repo
Framework

Probabilistically Safe Robot Planning with Confidence-Based Human Predictions


Title	Probabilistically Safe Robot Planning with Confidence-Based Human Predictions
Authors	Jaime F. Fisac, Andrea Bajcsy, Sylvia L. Herbert, David Fridovich-Keil, Steven Wang, Claire J. Tomlin, Anca D. Dragan
Abstract	In order to safely operate around humans, robots can employ predictive models of human motion. Unfortunately, these models cannot capture the full complexity of human behavior and necessarily introduce simplifying assumptions. As a result, predictions may degrade whenever the observed human behavior departs from the assumed structure, which can have negative implications for safety. In this paper, we observe that how “rational” human actions appear under a particular model can be viewed as an indicator of that model’s ability to describe the human’s current motion. By reasoning about this model confidence in a real-time Bayesian framework, we show that the robot can very quickly modulate its predictions to become more uncertain when the model performs poorly. Building on recent work in provably-safe trajectory planning, we leverage these confidence-aware human motion predictions to generate assured autonomous robot motion. Our new analysis combines worst-case tracking error guarantees for the physical robot with probabilistic time-varying human predictions, yielding a quantitative, probabilistic safety certificate. We demonstrate our approach with a quadcopter navigating around a human.
Tasks
Published	2018-05-31
URL	http://arxiv.org/abs/1806.00109v1
PDF	http://arxiv.org/pdf/1806.00109v1.pdf
PWC	https://paperswithcode.com/paper/probabilistically-safe-robot-planning-with
Repo
Framework