October 18, 2019

3211 words 16 mins read

Paper Group ANR 629

Paper Group ANR 629

DeepSOFA: A Continuous Acuity Score for Critically Ill Patients using Clinically Interpretable Deep Learning. Efficient Purely Convolutional Text Encoding. A deep learning approach for understanding natural language commands for mobile service robots. Linked Recurrent Neural Networks. Benchmarking Evolutionary Algorithms For Single Objective Real-v …

DeepSOFA: A Continuous Acuity Score for Critically Ill Patients using Clinically Interpretable Deep Learning

Title DeepSOFA: A Continuous Acuity Score for Critically Ill Patients using Clinically Interpretable Deep Learning
Authors Benjamin Shickel, Tyler J. Loftus, Lasith Adhikari, Tezcan Ozrazgat-Baslanti, Azra Bihorac, Parisa Rashidi
Abstract Traditional methods for assessing illness severity and predicting in-hospital mortality among critically ill patients require time-consuming, error-prone calculations using static variable thresholds. These methods do not capitalize on the emerging availability of streaming electronic health record data or capture time-sensitive individual physiological patterns, a critical task in the intensive care unit. We propose a novel acuity score framework (DeepSOFA) that leverages temporal measurements and interpretable deep learning models to assess illness severity at any point during an ICU stay. We compare DeepSOFA with SOFA (Sequential Organ Failure Assessment) baseline models using the same model inputs and find that at any point during an ICU admission, DeepSOFA yields significantly more accurate predictions of in-hospital mortality. A DeepSOFA model developed in a public database and validated in a single institutional cohort had a mean AUC for the entire ICU stay of 0.90 (95% CI 0.90-0.91) compared with baseline SOFA models with mean AUC 0.79 (95% CI 0.79-0.80) and 0.85 (95% CI 0.85-0.86). Deep models are well-suited to identify ICU patients in need of life-saving interventions prior to the occurrence of an unexpected adverse event and inform shared decision-making processes among patients, providers, and families regarding goals of care and optimal resource utilization.
Tasks Decision Making
Published 2018-02-28
URL http://arxiv.org/abs/1802.10238v4
PDF http://arxiv.org/pdf/1802.10238v4.pdf
PWC https://paperswithcode.com/paper/deepsofa-a-continuous-acuity-score-for
Repo
Framework

Efficient Purely Convolutional Text Encoding

Title Efficient Purely Convolutional Text Encoding
Authors Szymon Malik, Adrian Lancucki, Jan Chorowski
Abstract In this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences. Such representations are useful for building NLP systems, including conversational agents. Our work derives from a recently proposed recursive convolutional architecture for auto-encoding text paragraphs at byte level. We propose alternations that significantly reduce training time, the number of parameters, and improve auto-encoding accuracy. Finally, we evaluate the representations created by our model on tasks from SentEval benchmark suite, and show that it can serve as a better, yet fairly low-resource alternative to popular bag-of-words embeddings.
Tasks
Published 2018-08-03
URL http://arxiv.org/abs/1808.01160v1
PDF http://arxiv.org/pdf/1808.01160v1.pdf
PWC https://paperswithcode.com/paper/efficient-purely-convolutional-text-encoding
Repo
Framework

A deep learning approach for understanding natural language commands for mobile service robots

Title A deep learning approach for understanding natural language commands for mobile service robots
Authors Pedro Henrique Martins, Luís Custódio, Rodrigo Ventura
Abstract Using natural language to give instructions to robots is challenging, since natural language understanding is still largely an open problem. In this paper we address this problem by restricting our attention to commands modeled as one action, plus arguments (also known as slots). For action detection (also called intent detection) and slot filling various architectures of Recurrent Neural Networks and Long Short Term Memory (LSTM) networks were evaluated, having LSTMs achieved a superior accuracy. As the action requested may not fall within the robots capabilities, a Support Vector Machine(SVM) is used to determine whether it is or not. For the input of the neural networks, several word embedding algorithms were compared. Finally, to implement the system in a robot, a ROS package is created using a SMACH state machine. The proposed system is then evaluated both using well-known datasets and benchmarks in the context of domestic service robots.
Tasks Action Detection, Intent Detection, Slot Filling
Published 2018-07-09
URL http://arxiv.org/abs/1807.03053v1
PDF http://arxiv.org/pdf/1807.03053v1.pdf
PWC https://paperswithcode.com/paper/a-deep-learning-approach-for-understanding
Repo
Framework

Linked Recurrent Neural Networks

Title Linked Recurrent Neural Networks
Authors Zhiwei Wang, Yao Ma, Dawei Yin, Jiliang Tang
Abstract Recurrent Neural Networks (RNNs) have been proven to be effective in modeling sequential data and they have been applied to boost a variety of tasks such as document classification, speech recognition and machine translation. Most of existing RNN models have been designed for sequences assumed to be identically and independently distributed (i.i.d). However, in many real-world applications, sequences are naturally linked. For example, web documents are connected by hyperlinks; and genes interact with each other. On the one hand, linked sequences are inherently not i.i.d., which poses tremendous challenges to existing RNN models. On the other hand, linked sequences offer link information in addition to the sequential information, which enables unprecedented opportunities to build advanced RNN models. In this paper, we study the problem of RNN for linked sequences. In particular, we introduce a principled approach to capture link information and propose a linked Recurrent Neural Network (LinkedRNN), which models sequential and link information coherently. We conduct experiments on real-world datasets from multiple domains and the experimental results validate the effectiveness of the proposed framework.
Tasks Document Classification, Machine Translation, Speech Recognition
Published 2018-08-19
URL http://arxiv.org/abs/1808.06170v1
PDF http://arxiv.org/pdf/1808.06170v1.pdf
PWC https://paperswithcode.com/paper/linked-recurrent-neural-networks
Repo
Framework

Benchmarking Evolutionary Algorithms For Single Objective Real-valued Constrained Optimization - A Critical Review

Title Benchmarking Evolutionary Algorithms For Single Objective Real-valued Constrained Optimization - A Critical Review
Authors Michael Hellwig, Hans-Georg Beyer
Abstract Benchmarking plays an important role in the development of novel search algorithms as well as for the assessment and comparison of contemporary algorithmic ideas. This paper presents common principles that need to be taken into account when considering benchmarking problems for constrained optimization. Current benchmark environments for testing Evolutionary Algorithms are reviewed in the light of these principles. Along with this line, the reader is provided with an overview of the available problem domains in the field of constrained benchmarking. Hence, the review supports algorithms developers with information about the merits and demerits of the available frameworks.
Tasks
Published 2018-06-12
URL http://arxiv.org/abs/1806.04563v2
PDF http://arxiv.org/pdf/1806.04563v2.pdf
PWC https://paperswithcode.com/paper/benchmarking-evolutionary-algorithms-for
Repo
Framework

Learning to Discriminate Noises for Incorporating External Information in Neural Machine Translation

Title Learning to Discriminate Noises for Incorporating External Information in Neural Machine Translation
Authors Zaixiang Zheng, Shujian Huang, Zewei Sun, Rongxiang Weng, Xin-Yu Dai, Jiajun Chen
Abstract Previous studies show that incorporating external information could improve the translation quality of Neural Machine Translation (NMT) systems. However, there are inevitably noises in the external information, severely reducing the benefit that the existing methods could receive from the incorporation. To tackle the problem, this study pays special attention to the discrimination of the noises during the incorporation. We argue that there exist two kinds of noise in this external information, i.e. global noise and local noise, which affect the translations for the whole sentence and for some specific words, respectively. Accordingly, we propose a general framework that learns to jointly discriminate both the global and local noises, so that the external information could be better leveraged. Our model is trained on the dataset derived from the original parallel corpus without any external labeled data or annotation. Experimental results in various real-world scenarios, language pairs, and neural architectures indicate that discriminating noises contributes to significant improvements in translation quality by being able to better incorporate the external information, even in very noisy conditions.
Tasks Machine Translation
Published 2018-10-24
URL http://arxiv.org/abs/1810.10317v3
PDF http://arxiv.org/pdf/1810.10317v3.pdf
PWC https://paperswithcode.com/paper/learning-to-discriminate-noises-for
Repo
Framework

Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector

Title Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector
Authors Jia-Xing Zhong, Nannan Li, Weijie Kong, Tao Zhang, Thomas H. Li, Ge Li
Abstract Weakly supervised temporal action detection is a Herculean task in understanding untrimmed videos, since no supervisory signal except the video-level category label is available on training data. Under the supervision of category labels, weakly supervised detectors are usually built upon classifiers. However, there is an inherent contradiction between classifier and detector; i.e., a classifier in pursuit of high classification performance prefers top-level discriminative video clips that are extremely fragmentary, whereas a detector is obliged to discover the whole action instance without missing any relevant snippet. To reconcile this contradiction, we train a detector by driving a series of classifiers to find new actionness clips progressively, via step-by-step erasion from a complete video. During the test phase, all we need to do is to collect detection results from the one-by-one trained classifiers at various erasing steps. To assist in the collection process, a fully connected conditional random field is established to refine the temporal localization outputs. We evaluate our approach on two prevailing datasets, THUMOS’14 and ActivityNet. The experiments show that our detector advances state-of-the-art weakly supervised temporal action detection results, and even compares with quite a few strongly supervised methods.
Tasks Action Detection, Temporal Localization
Published 2018-07-09
URL http://arxiv.org/abs/1807.02929v2
PDF http://arxiv.org/pdf/1807.02929v2.pdf
PWC https://paperswithcode.com/paper/step-by-step-erasion-one-by-one-collection-a
Repo
Framework

A Comparative Study of Computational Aesthetics

Title A Comparative Study of Computational Aesthetics
Authors Dogancan Temel, Ghassan AlRegib
Abstract Objective metrics model image quality by quantifying image degradations or estimating perceived image quality. However, image quality metrics do not model what makes an image more appealing or beautiful. In order to quantify the aesthetics of an image, we need to take it one step further and model the perception of aesthetics. In this paper, we examine computational aesthetics models that use hand-crafted, generic and hybrid descriptors. We show that generic descriptors can perform as well as state of the art hand-crafted aesthetics models that use global features. However, neither generic nor hand-crafted features is sufficient to model aesthetics when we only use global features without considering spatial composition or distribution. We also follow a visual dictionary approach similar to state of the art methods and show that it performs poorly without the spatial pyramid step.
Tasks
Published 2018-11-19
URL http://arxiv.org/abs/1811.08012v1
PDF http://arxiv.org/pdf/1811.08012v1.pdf
PWC https://paperswithcode.com/paper/a-comparative-study-of-computational
Repo
Framework

A Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalization

Title A Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalization
Authors Alina Marcu, Dragos Costea, Emil Slusanschi, Marius Leordeanu
Abstract Semantic segmentation and vision-based geolocalization in aerial images are challenging tasks in computer vision. Due to the advent of deep convolutional nets and the availability of relatively low cost UAVs, they are currently generating a growing attention in the field. We propose a novel multi-task multi-stage neural network that is able to handle the two problems at the same time, in a single forward pass. The first stage of our network predicts pixelwise class labels, while the second stage provides a precise location using two branches. One branch uses a regression network, while the other is used to predict a location map trained as a segmentation task. From a structural point of view, our architecture uses encoder-decoder modules at each stage, having the same encoder structure re-used. Furthermore, its size is limited to be tractable on an embedded GPU. We achieve commercial GPS-level localization accuracy from satellite images with spatial resolution of 1 square meter per pixel in a city-wide area of interest. On the task of semantic segmentation, we obtain state-of-the-art results on two challenging datasets, the Inria Aerial Image Labeling dataset and Massachusetts Buildings.
Tasks Semantic Segmentation
Published 2018-04-04
URL http://arxiv.org/abs/1804.01322v1
PDF http://arxiv.org/pdf/1804.01322v1.pdf
PWC https://paperswithcode.com/paper/a-multi-stage-multi-task-neural-network-for
Repo
Framework

Enabling Cognitive Smart Cities Using Big Data and Machine Learning: Approaches and Challenges

Title Enabling Cognitive Smart Cities Using Big Data and Machine Learning: Approaches and Challenges
Authors Mehdi Mohammadi, Ala Al-Fuqaha
Abstract The development of smart cities and their fast-paced deployment is resulting in the generation of large quantities of data at unprecedented rates. Unfortunately, most of the generated data is wasted without extracting potentially useful information and knowledge because of the lack of established mechanisms and standards that benefit from the availability of such data. Moreover, the high dynamical nature of smart cities calls for new generation of machine learning approaches that are flexible and adaptable to cope with the dynamicity of data to perform analytics and learn from real-time data. In this article, we shed the light on the challenge of under utilizing the big data generated by smart cities from a machine learning perspective. Especially, we present the phenomenon of wasting unlabeled data. We argue that semi-supervision is a must for smart city to address this challenge. We also propose a three-level learning framework for smart cities that matches the hierarchical nature of big data generated by smart cities with a goal of providing different levels of knowledge abstractions. The proposed framework is scalable to meet the needs of smart city services. Fundamentally, the framework benefits from semi-supervised deep reinforcement learning where a small amount of data that has users’ feedback serves as labeled data while a larger amount is without such users’ feedback serves as unlabeled data. This paper also explores how deep reinforcement learning and its shift toward semi-supervision can handle the cognitive side of smart city services and improve their performance by providing several use cases spanning the different domains of smart cities. We also highlight several challenges as well as promising future research directions for incorporating machine learning and high-level intelligence into smart city services.
Tasks
Published 2018-10-09
URL http://arxiv.org/abs/1810.04107v1
PDF http://arxiv.org/pdf/1810.04107v1.pdf
PWC https://paperswithcode.com/paper/enabling-cognitive-smart-cities-using-big
Repo
Framework

Weakly Supervised Salient Object Detection Using Image Labels

Title Weakly Supervised Salient Object Detection Using Image Labels
Authors Guanbin Li, Yuan Xie, Liang Lin
Abstract Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure. In this paper, we note that superior salient object detection can be obtained by iteratively mining and correcting the labeling ambiguity on saliency maps from traditional unsupervised methods. We propose to use the combination of a coarse salient object activation map from the classification network and saliency maps generated from unsupervised methods as pixel-level annotation, and develop a simple yet very effective algorithm to train fully convolutional networks for salient object detection supervised by these noisy annotations. Our algorithm is based on alternately exploiting a graphical model and training a fully convolutional network for model updating. The graphical model corrects the internal labeling ambiguity through spatial consistency and structure preserving while the fully convolutional network helps to correct the cross-image semantic ambiguity and simultaneously update the coarse activation map for next iteration. Experimental results demonstrate that our proposed method greatly outperforms all state-of-the-art unsupervised saliency detection methods and can be comparable to the current best strongly-supervised methods training with thousands of pixel-level saliency map annotations on all public benchmarks.
Tasks Object Detection, Saliency Detection, Salient Object Detection
Published 2018-03-17
URL http://arxiv.org/abs/1803.06503v1
PDF http://arxiv.org/pdf/1803.06503v1.pdf
PWC https://paperswithcode.com/paper/weakly-supervised-salient-object-detection
Repo
Framework

A Robust Local Binary Similarity Pattern for Foreground Object Detection

Title A Robust Local Binary Similarity Pattern for Foreground Object Detection
Authors Dongdong Zeng, Ming Zhu, Hang Yang
Abstract Accurate and fast extraction of the foreground object is one of the most significant issues to be solved due to its important meaning for object tracking and recognition in video surveillance. Although many foreground object detection methods have been proposed in the recent past, it is still regarded as a tough problem due to illumination variations and dynamic backgrounds challenges. In this paper, we propose a robust foreground object detection method with two aspects of contributions. First, we propose a robust texture operator named Robust Local Binary Similarity Pattern (RLBSP), which shows strong robustness to illumination variations and dynamic backgrounds. Second, a combination of color and texture features are used to characterize pixel representations, which compensate each other to make full use of their own advantages. Comprehensive experiments evaluated on the CDnet 2012 dataset demonstrate that the proposed method performs favorably against state-of-the-art methods.
Tasks Object Detection, Object Tracking
Published 2018-10-16
URL http://arxiv.org/abs/1810.06797v2
PDF http://arxiv.org/pdf/1810.06797v2.pdf
PWC https://paperswithcode.com/paper/a-robust-local-binary-similarity-pattern-for
Repo
Framework

Neuro-memristive Circuits for Edge Computing: A review

Title Neuro-memristive Circuits for Edge Computing: A review
Authors Olga Krestinskaya, Alex Pappachen James, Leon O. Chua
Abstract The volume, veracity, variability, and velocity of data produced from the ever-increasing network of sensors connected to Internet pose challenges for power management, scalability, and sustainability of cloud computing infrastructure. Increasing the data processing capability of edge computing devices at lower power requirements can reduce several overheads for cloud computing solutions. This paper provides the review of neuromorphic CMOS-memristive architectures that can be integrated into edge computing devices. We discuss why the neuromorphic architectures are useful for edge devices and show the advantages, drawbacks and open problems in the field of neuro-memristive circuits for edge computing.
Tasks
Published 2018-07-01
URL http://arxiv.org/abs/1807.00962v2
PDF http://arxiv.org/pdf/1807.00962v2.pdf
PWC https://paperswithcode.com/paper/neuro-memristive-circuits-for-edge-computing
Repo
Framework

PAC Battling Bandits in the Plackett-Luce Model

Title PAC Battling Bandits in the Plackett-Luce Model
Authors Aadirupa Saha, Aditya Gopalan
Abstract We introduce the probably approximately correct (PAC) \emph{Battling-Bandit} problem with the Plackett-Luce (PL) subset choice model–an online learning framework where at each trial the learner chooses a subset of $k$ arms from a fixed set of $n$ arms, and subsequently observes a stochastic feedback indicating preference information of the items in the chosen subset, e.g., the most preferred item or ranking of the top $m$ most preferred items etc. The objective is to identify a near-best item in the underlying PL model with high confidence. This generalizes the well-studied PAC \emph{Dueling-Bandit} problem over $n$ arms, which aims to recover the \emph{best-arm} from pairwise preference information, and is known to require $O(\frac{n}{\epsilon^2} \ln \frac{1}{\delta})$ sample complexity \citep{Busa_pl,Busa_top}. We study the sample complexity of this problem under various feedback models: (1) Winner of the subset (WI), and (2) Ranking of top-$m$ items (TR) for $2\le m \le k$. We show, surprisingly, that with winner information (WI) feedback over subsets of size $2 \leq k \leq n$, the best achievable sample complexity is still $O\left( \frac{n}{\epsilon^2} \ln \frac{1}{\delta}\right)$, independent of $k$, and the same as that in the Dueling Bandit setting ($k=2$). For the more general top-$m$ ranking (TR) feedback model, we show a significantly smaller lower bound on sample complexity of $\Omega\bigg( \frac{n}{m\epsilon^2} \ln \frac{1}{\delta}\bigg)$, which suggests a multiplicative reduction by a factor ${m}$ owing to the additional information revealed from preferences among $m$ items instead of just $1$. We also propose two algorithms for the PAC problem with the TR feedback model with optimal (upto logarithmic factors) sample complexity guarantees, establishing the increase in statistical efficiency from exploiting rank-ordered feedback.
Tasks
Published 2018-08-12
URL http://arxiv.org/abs/1808.04008v3
PDF http://arxiv.org/pdf/1808.04008v3.pdf
PWC https://paperswithcode.com/paper/pac-battling-bandits-in-the-plackett-luce
Repo
Framework
Title Marketing Analytics: Methods, Practice, Implementation, and Links to Other Fields
Authors Stephen L. France, Sanjoy Ghose
Abstract Marketing analytics is a diverse field, with both academic researchers and practitioners coming from a range of backgrounds including marketing, expert systems, statistics, and operations research. This paper provides an integrative review at the boundary of these areas. The aim is to give researchers in the intelligent and expert systems community the opportunity to gain a broad view of the marketing analytics area and provide a starting point for future interdisciplinary collaboration. The topics of visualization, segmentation, and class prediction are featured. Links between the disciplines are emphasized. For each of these topics, a historical overview is given, starting with initial work in the 1960s and carrying through to the present day. Recent innovations for modern, large, and complex “big data” sets are described. Practical implementation advice is given, along with a directory of open source R routines for implementing marketing analytics techniques.
Tasks
Published 2018-01-28
URL http://arxiv.org/abs/1801.09185v2
PDF http://arxiv.org/pdf/1801.09185v2.pdf
PWC https://paperswithcode.com/paper/marketing-analytics-methods-practice
Repo
Framework
comments powered by Disqus