Paper Group ANR 1063
Domain Adaptation for Infection Prediction from Symptoms Based on Data from Different Study Designs and Contexts. A Deep Q-Learning Agent for the L-Game with Variable Batch Training. Memetic Algorithms Beat Evolutionary Algorithms on the Class of Hurdle Problems. Word Segmentation as Graph Partition. Universal Neural Machine Translation for Extreme …
Domain Adaptation for Infection Prediction from Symptoms Based on Data from Different Study Designs and Contexts
| Title | Domain Adaptation for Infection Prediction from Symptoms Based on Data from Different Study Designs and Contexts |
| Authors | Nabeel Abdur Rehman, Maxwell Matthaios Aliapoulios, Disha Umarwani, Rumi Chunara |
| Abstract | Acute respiratory infections have epidemic and pandemic potential and thus are being studied worldwide, albeit in many different contexts and study formats. Predicting infection from symptom data is critical, though using symptom data from varied studies in aggregate is challenging because the data is collected in different ways. Accordingly, different symptom profiles could be more predictive in certain studies, or even symptoms of the same name could have different meanings in different contexts. We assess state-of-the-art transfer learning methods for improving prediction of infection from symptom data in multiple types of health care data ranging from clinical, to home-visit as well as crowdsourced studies. We show interesting characteristics regarding six different study types and their feature domains. Further, we demonstrate that it is possible to use data collected from one study to predict infection in another, at close to or better than using a single dataset for prediction on itself. We also investigate in which conditions specific transfer learning and domain adaptation methods may perform better on symptom data. This work has the potential for broad applicability as we show how it is possible to transfer learning from one public health study design to another, and data collected from one study may be used for prediction of labels for another, even collected through different study designs, populations and contexts. |
| Tasks | Domain Adaptation, Transfer Learning |
| Published | 2018-06-22 |
| URL | http://arxiv.org/abs/1806.08835v1 |
| http://arxiv.org/pdf/1806.08835v1.pdf | |
| PWC | https://paperswithcode.com/paper/domain-adaptation-for-infection-prediction |
| Repo | |
| Framework | |
A Deep Q-Learning Agent for the L-Game with Variable Batch Training
| Title | A Deep Q-Learning Agent for the L-Game with Variable Batch Training |
| Authors | Petros Giannakopoulos, Yannis Cotronis |
| Abstract | We employ the Deep Q-Learning algorithm with Experience Replay to train an agent capable of achieving a high-level of play in the L-Game while self-learning from low-dimensional states. We also employ variable batch size for training in order to mitigate the loss of the rare reward signal and significantly accelerate training. Despite the large action space due to the number of possible moves, the low-dimensional state space and the rarity of rewards, which only come at the end of a game, DQL is successful in training an agent capable of strong play without the use of any search methods or domain knowledge. |
| Tasks | Q-Learning |
| Published | 2018-02-17 |
| URL | http://arxiv.org/abs/1802.06225v1 |
| http://arxiv.org/pdf/1802.06225v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-q-learning-agent-for-the-l-game-with |
| Repo | |
| Framework | |
Memetic Algorithms Beat Evolutionary Algorithms on the Class of Hurdle Problems
| Title | Memetic Algorithms Beat Evolutionary Algorithms on the Class of Hurdle Problems |
| Authors | Phan Trung Hai Nguyen, Dirk Sudholt |
| Abstract | Memetic algorithms are popular hybrid search heuristics that integrate local search into the search process of an evolutionary algorithm in order to combine the advantages of rapid exploitation and global optimisation. However, these algorithms are not well understood and the field is lacking a solid theoretical foundation that explains when and why memetic algorithms are effective. We provide a rigorous runtime analysis of a simple memetic algorithm, the $(1+1)$ MA, on the Hurdle problem class, a landscape class of tuneable difficulty that shows a “big valley structure”, a characteristic feature of many hard problems from combinatorial optimisation. The only parameter of this class is the hurdle width w, which describes the length of fitness valleys that have to be overcome. We show that the $(1+1)$ EA requires $\Theta(n^w)$ expected function evaluations to find the optimum, whereas the $(1+1)$ MA with best-improvement and first-improvement local search can find the optimum in $\Theta(n^2+n^3/w^2)$ and $\Theta(n^3/w^2)$ function evaluations, respectively. Surprisingly, while increasing the hurdle width makes the problem harder for evolutionary algorithms, the problem becomes easier for memetic algorithms. We discuss how these findings can explain and illustrate the success of memetic algorithms for problems with big valley structures. |
| Tasks | |
| Published | 2018-04-17 |
| URL | http://arxiv.org/abs/1804.06173v1 |
| http://arxiv.org/pdf/1804.06173v1.pdf | |
| PWC | https://paperswithcode.com/paper/memetic-algorithms-beat-evolutionary |
| Repo | |
| Framework | |
Word Segmentation as Graph Partition
| Title | Word Segmentation as Graph Partition |
| Authors | Yuanhao Liu, Sheng Yu |
| Abstract | We propose a new approach to the Chinese word segmentation problem that considers the sentence as an undirected graph, whose nodes are the characters. One can use various techniques to compute the edge weights that measure the connection strength between characters. Spectral graph partition algorithms are used to group the characters and achieve word segmentation. We follow the graph partition approach and design several unsupervised algorithms, and we show their inspiring segmentation results on two corpora: (1) electronic health records in Chinese, and (2) benchmark data from the Second International Chinese Word Segmentation Bakeoff. |
| Tasks | Chinese Word Segmentation |
| Published | 2018-04-05 |
| URL | http://arxiv.org/abs/1804.01778v1 |
| http://arxiv.org/pdf/1804.01778v1.pdf | |
| PWC | https://paperswithcode.com/paper/word-segmentation-as-graph-partition |
| Repo | |
| Framework | |
Universal Neural Machine Translation for Extremely Low Resource Languages
| Title | Universal Neural Machine Translation for Extremely Low Resource Languages |
| Authors | Jiatao Gu, Hany Hassan, Jacob Devlin, Victor O. K. Li |
| Abstract | In this paper, we propose a new universal machine translation approach focusing on languages with a limited amount of parallel data. Our proposed approach utilizes a transfer-learning approach to share lexical and sentence level representations across multiple source languages into one target language. The lexical part is shared through a Universal Lexical Representation to support multilingual word-level sharing. The sentence-level sharing is represented by a model of experts from all source languages that share the source encoders with all other languages. This enables the low-resource language to utilize the lexical and sentence representations of the higher resource languages. Our approach is able to achieve 23 BLEU on Romanian-English WMT2016 using a tiny parallel corpus of 6k sentences, compared to the 18 BLEU of strong baseline system which uses multilingual training and back-translation. Furthermore, we show that the proposed approach can achieve almost 20 BLEU on the same dataset through fine-tuning a pre-trained multi-lingual system in a zero-shot setting. |
| Tasks | Machine Translation, Transfer Learning |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1802.05368v2 |
| http://arxiv.org/pdf/1802.05368v2.pdf | |
| PWC | https://paperswithcode.com/paper/universal-neural-machine-translation-for |
| Repo | |
| Framework | |
ASP:A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction
| Title | ASP:A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction |
| Authors | Fuxun Yu, Qide Dong, Xiang Chen |
| Abstract | With the excellent accuracy and feasibility, the Neural Networks have been widely applied into the novel intelligent applications and systems. However, with the appearance of the Adversarial Attack, the NN based system performance becomes extremely vulnerable:the image classification results can be arbitrarily misled by the adversarial examples, which are crafted images with human unperceivable pixel-level perturbation. As this raised a significant system security issue, we implemented a series of investigations on the adversarial attack in this work: We first identify an image’s pixel vulnerability to the adversarial attack based on the adversarial saliency analysis. By comparing the analyzed saliency map and the adversarial perturbation distribution, we proposed a new evaluation scheme to comprehensively assess the adversarial attack precision and efficiency. Then, with a novel adversarial saliency prediction method, a fast adversarial example generation framework, namely “ASP”, is proposed with significant attack efficiency improvement and dramatic computation cost reduction. Compared to the previous methods, experiments show that ASP has at most 12 times speed-up for adversarial example generation, 2 times lower perturbation rate, and high attack success rate of 87% on both MNIST and Cifar10. ASP can be also well utilized to support the data-hungry NN adversarial training. By reducing the attack success rate as much as 90%, ASP can quickly and effectively enhance the defense capability of NN based system to the adversarial attacks. |
| Tasks | Adversarial Attack, Image Classification, Saliency Prediction |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1802.05763v3 |
| http://arxiv.org/pdf/1802.05763v3.pdf | |
| PWC | https://paperswithcode.com/paper/aspa-fast-adversarial-attack-example |
| Repo | |
| Framework | |
Autonomous drone cinematographer: Using artistic principles to create smooth, safe, occlusion-free trajectories for aerial filming
| Title | Autonomous drone cinematographer: Using artistic principles to create smooth, safe, occlusion-free trajectories for aerial filming |
| Authors | Rogerio Bonatti, Yanfu Zhang, Sanjiban Choudhury, Wenshan Wang, Sebastian Scherer |
| Abstract | Autonomous aerial cinematography has the potential to enable automatic capture of aesthetically pleasing videos without requiring human intervention, empowering individuals with the capability of high-end film studios. Current approaches either only handle off-line trajectory generation, or offer strategies that reason over short time horizons and simplistic representations for obstacles, which result in jerky movement and low real-life applicability. In this work we develop a method for aerial filming that is able to trade off shot smoothness, occlusion, and cinematography guidelines in a principled manner, even under noisy actor predictions. We present a novel algorithm for real-time covariant gradient descent that we use to efficiently find the desired trajectories by optimizing a set of cost functions. Experimental results show that our approach creates attractive shots, avoiding obstacles and occlusion 65 times over 1.25 hours of flight time, re-planning at 5 Hz with a 10 s time horizon. We robustly film human actors, cars and bicycles performing different motion among obstacles, using various shot types. |
| Tasks | |
| Published | 2018-08-28 |
| URL | http://arxiv.org/abs/1808.09563v1 |
| http://arxiv.org/pdf/1808.09563v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-drone-cinematographer-using |
| Repo | |
| Framework | |
Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information
| Title | Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information |
| Authors | Arjun Sharma, Mohit Sharma, Nicholas Rhinehart, Kris M. Kitani |
| Abstract | The use of imitation learning to learn a single policy for a complex task that has multiple modes or hierarchical structure can be challenging. In fact, previous work has shown that when the modes are known, learning separate policies for each mode or sub-task can greatly improve the performance of imitation learning. In this work, we discover the interaction between sub-tasks from their resulting state-action trajectory sequences using a directed graphical model. We propose a new algorithm based on the generative adversarial imitation learning framework which automatically learns sub-task policies from unsegmented demonstrations. Our approach maximizes the directed information flow in the graphical model between sub-task latent variables and their generated trajectories. We also show how our approach connects with the existing Options framework, which is commonly used to learn hierarchical policies. |
| Tasks | Imitation Learning |
| Published | 2018-09-29 |
| URL | http://arxiv.org/abs/1810.01266v2 |
| http://arxiv.org/pdf/1810.01266v2.pdf | |
| PWC | https://paperswithcode.com/paper/directed-info-gail-learning-hierarchical |
| Repo | |
| Framework | |
Multinomial logistic model for coinfection diagnosis between arbovirus and malaria in Kedougou
| Title | Multinomial logistic model for coinfection diagnosis between arbovirus and malaria in Kedougou |
| Authors | Mor Absa Loum, Marie-Anne Poursat, Abdourahmane Sow, Amadou Sall, Cheikh Loucoubar, Elisabeth Gassiat |
| Abstract | In tropical regions, populations continue to suffer morbidity and mortality from malaria and arboviral diseases. In Kedougou (Senegal), these illnesses are all endemic due to the climate and its geographical position. The co-circulation of malaria parasites and arboviruses can explain the observation of coinfected cases. Indeed there is strong resemblance in symptoms between these diseases making problematic targeted medical care of coinfected cases. This is due to the fact that the origin of illness is not obviously known. Some cases could be immunized against one or the other of the pathogens, immunity typically acquired with factors like age and exposure as usual for endemic area. Then, coinfection needs to be better diagnosed. Using data collected from patients in Kedougou region, from 2009 to 2013, we adjusted a multinomial logistic model and selected relevant variables in explaining coinfection status. We observed specific sets of variables explaining each of the diseases exclusively and the coinfection. We tested the independence between arboviral and malaria infections and derived coinfection probabilities from the model fitting. In case of a coinfection probability greater than a threshold value to be calibrated on the data, duration of illness above 3 days and age above 10 years-old are mostly indicative of arboviral disease while body temperature higher than 40{\textdegree}C and presence of nausea or vomiting symptoms during the rainy season are mostly indicative of malaria disease. |
| Tasks | |
| Published | 2018-01-12 |
| URL | https://arxiv.org/abs/1801.04212v2 |
| https://arxiv.org/pdf/1801.04212v2.pdf | |
| PWC | https://paperswithcode.com/paper/multinomial-logistic-model-for-coinfection |
| Repo | |
| Framework | |
Plan in 2D, execute in 3D: An augmented reality solution for cup placement in total hip arthroplasty
| Title | Plan in 2D, execute in 3D: An augmented reality solution for cup placement in total hip arthroplasty |
| Authors | Javad Fotouhi, Clayton P. Alexander, Mathias Unberath, Giacomo Taylor, Sing Chun Lee, Bernhard Fuerst, Alex Johnson, Greg Osgood, Russell H. Taylor, Harpal Khanuja, Mehran Armand, Nassir Navab |
| Abstract | Reproducibly achieving proper implant alignment is a critical step in total hip arthroplasty (THA) procedures that has been shown to substantially affect patient outcome. In current practice, correct alignment of the acetabular cup is verified in C-arm X-ray images that are acquired in an anterior-posterior (AP) view. Favorable surgical outcome is, therefore, heavily dependent on the surgeon’s experience in understanding the 3D orientation of a hemispheric implant from 2D AP projection images. This work proposes an easy to use intra-operative component planning system based on two C-arm X-ray images that is combined with 3D augmented reality (AR) visualization that simplifies impactor and cup placement according to the planning by providing a real-time RGBD data overlay. We evaluate the feasibility of our system in a user study comprising four orthopedic surgeons at the Johns Hopkins Hospital, and also report errors in translation, anteversion, and abduction as low as 1.98 mm, 1.10 degrees, and 0.53 degrees, respectively. The promising performance of this AR solution shows that deploying this system could eliminate the need for excessive radiation, simplify the intervention, and enable reproducibly accurate placement of acetabular implants. |
| Tasks | |
| Published | 2018-01-04 |
| URL | http://arxiv.org/abs/1801.01557v1 |
| http://arxiv.org/pdf/1801.01557v1.pdf | |
| PWC | https://paperswithcode.com/paper/plan-in-2d-execute-in-3d-an-augmented-reality |
| Repo | |
| Framework | |
Autonomous Configuration of Network Parameters in Operating Systems using Evolutionary Algorithms
| Title | Autonomous Configuration of Network Parameters in Operating Systems using Evolutionary Algorithms |
| Authors | Bartosz Gembala, Anis Yazidi, Hårek Haugerud, Stefano Nichele |
| Abstract | By default, the Linux network stack is not configured for highspeed large file transfer. The reason behind this is to save memory resources. It is possible to tune the Linux network stack by increasing the network buffers size for high-speed networks that connect server systems in order to handle more network packets. However, there are also several other TCP/IP parameters that can be tuned in an Operating System (OS). In this paper, we leverage Genetic Algorithms (GAs) to devise a system which learns from the history of the network traffic and uses this knowledge to optimize the current performance by adjusting the parameters. This can be done for a standard Linux kernel using sysctl or /proc. For a Virtual Machine (VM), virtually any type of OS can be installed and an image can swiftly be compiled and deployed. By being a sandboxed environment, risky configurations can be tested without the danger of harming the system. Different scenarios for network parameter configurations are thoroughly tested, and an increase of up to 65% throughput speed is achieved compared to the default Linux configuration. |
| Tasks | |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1808.10733v1 |
| http://arxiv.org/pdf/1808.10733v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-configuration-of-network |
| Repo | |
| Framework | |
Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation
| Title | Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation |
| Authors | Yudong Chen, Yuejie Chi |
| Abstract | Low-rank modeling plays a pivotal role in signal processing and machine learning, with applications ranging from collaborative filtering, video surveillance, medical imaging, to dimensionality reduction and adaptive filtering. Many modern high-dimensional data and interactions thereof can be modeled as lying approximately in a low-dimensional subspace or manifold, possibly with additional structures, and its proper exploitations lead to significant reduction of costs in sensing, computation and storage. In recent years, there is a plethora of progress in understanding how to exploit low-rank structures using computationally efficient procedures in a provable manner, including both convex and nonconvex approaches. On one side, convex relaxations such as nuclear norm minimization often lead to statistically optimal procedures for estimating low-rank matrices, where first-order methods are developed to address the computational challenges; on the other side, there is emerging evidence that properly designed nonconvex procedures, such as projected gradient descent, often provide globally optimal solutions with a much lower computational cost in many problems. This survey article will provide a unified overview of these recent advances on low-rank matrix estimation from incomplete measurements. Attention is paid to rigorous characterization of the performance of these algorithms, and to problems where the low-rank matrix have additional structural properties that require new algorithmic designs and theoretical analysis. |
| Tasks | Dimensionality Reduction |
| Published | 2018-02-23 |
| URL | http://arxiv.org/abs/1802.08397v3 |
| http://arxiv.org/pdf/1802.08397v3.pdf | |
| PWC | https://paperswithcode.com/paper/harnessing-structures-in-big-data-via |
| Repo | |
| Framework | |
Probabilistic Plant Modeling via Multi-View Image-to-Image Translation
| Title | Probabilistic Plant Modeling via Multi-View Image-to-Image Translation |
| Authors | Takahiro Isokane, Fumio Okura, Ayaka Ide, Yasuyuki Matsushita, Yasushi Yagi |
| Abstract | This paper describes a method for inferring three-dimensional (3D) plant branch structures that are hidden under leaves from multi-view observations. Unlike previous geometric approaches that heavily rely on the visibility of the branches or use parametric branching models, our method makes statistical inferences of branch structures in a probabilistic framework. By inferring the probability of branch existence using a Bayesian extension of image-to-image translation applied to each of multi-view images, our method generates a probabilistic plant 3D model, which represents the 3D branching pattern that cannot be directly observed. Experiments demonstrate the usefulness of the proposed approach in generating convincing branch structures in comparison to prior approaches. |
| Tasks | Image-to-Image Translation |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09404v1 |
| http://arxiv.org/pdf/1804.09404v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-plant-modeling-via-multi-view |
| Repo | |
| Framework | |
On-the-fly Augmented Reality for Orthopaedic Surgery Using a Multi-Modal Fiducial
| Title | On-the-fly Augmented Reality for Orthopaedic Surgery Using a Multi-Modal Fiducial |
| Authors | Sebastian Andress, Alex Johnson, Mathias Unberath, Alexander Winkler, Kevin Yu, Javad Fotouhi, Simon Weidert, Greg Osgood, Nassir Navab |
| Abstract | Fluoroscopic X-ray guidance is a cornerstone for percutaneous orthopaedic surgical procedures. However, two-dimensional observations of the three-dimensional anatomy suffer from the effects of projective simplification. Consequently, many X-ray images from various orientations need to be acquired for the surgeon to accurately assess the spatial relations between the patient’s anatomy and the surgical tools. In this paper, we present an on-the-fly surgical support system that provides guidance using augmented reality and can be used in quasi-unprepared operating rooms. The proposed system builds upon a multi-modality marker and simultaneous localization and mapping technique to co-calibrate an optical see-through head mounted display to a C-arm fluoroscopy system. Then, annotations on the 2D X-ray images can be rendered as virtual objects in 3D providing surgical guidance. We quantitatively evaluate the components of the proposed system, and finally, design a feasibility study on a semi-anthropomorphic phantom. The accuracy of our system was comparable to the traditional image-guided technique while substantially reducing the number of acquired X-ray images as well as procedure time. Our promising results encourage further research on the interaction between virtual and real objects, that we believe will directly benefit the proposed method. Further, we would like to explore the capabilities of our on-the-fly augmented reality support system in a larger study directed towards common orthopaedic interventions. |
| Tasks | Simultaneous Localization and Mapping |
| Published | 2018-01-04 |
| URL | http://arxiv.org/abs/1801.01560v1 |
| http://arxiv.org/pdf/1801.01560v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-fly-augmented-reality-for-orthopaedic |
| Repo | |
| Framework | |
Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers
| Title | Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers |
| Authors | Nathan Inkawhich, Matthew Inkawhich, Yiran Chen, Hai Li |
| Abstract | The success of deep learning research has catapulted deep models into production systems that our society is becoming increasingly dependent on, especially in the image and video domains. However, recent work has shown that these largely uninterpretable models exhibit glaring security vulnerabilities in the presence of an adversary. In this work, we develop a powerful untargeted adversarial attack for action recognition systems in both white-box and black-box settings. Action recognition models differ from image-classification models in that their inputs contain a temporal dimension, which we explicitly target in the attack. Drawing inspiration from image classifier attacks, we create new attacks which achieve state-of-the-art success rates on a two-stream classifier trained on the UCF-101 dataset. We find that our attacks can significantly degrade a model’s performance with sparsely and imperceptibly perturbed examples. We also demonstrate the transferability of our attacks to black-box action recognition systems. |
| Tasks | Adversarial Attack, Image Classification, Optical Flow Estimation, Temporal Action Localization |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.11875v1 |
| http://arxiv.org/pdf/1811.11875v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-attacks-for-optical-flow-based |
| Repo | |
| Framework | |
