October 16, 2019

2868 words 14 mins read

Paper Group ANR 1019

Studying the Effects of Deep Brain Stimulation and Medication on the Dynamics of STN-LFP Signals for Human Behavior Analysis. Staff line Removal using Generative Adversarial Networks. Recent Progress on Graph Partitioning Problems Using Evolutionary Computation. Joint Neural Entity Disambiguation with Output Space Search. English-Catalan Neural Mac …

Studying the Effects of Deep Brain Stimulation and Medication on the Dynamics of STN-LFP Signals for Human Behavior Analysis


Title	Studying the Effects of Deep Brain Stimulation and Medication on the Dynamics of STN-LFP Signals for Human Behavior Analysis
Authors	Hosein M. Golshan, Adam O. Hebb, Joshua Nedrud, Mohammad H. Mahoor
Abstract	This paper presents the results of our recent work on studying the effects of deep brain stimulation (DBS) and medication on the dynamics of brain local field potential (LFP) signals used for behavior analysis of patients with Parkinson s disease (PD). DBS is a technique used to alleviate the severe symptoms of PD when pharmacotherapy is not very effective. Behavior recognition from the LFP signals recorded from the subthalamic nucleus (STN) has application in developing closed-loop DBS systems, where the stimulation pulse is adaptively generated according to subjects performing behavior. Most of the existing studies on behavior recognition that use STN-LFPs are based on the DBS being off. This paper discovers how the performance and accuracy of automated behavior recognition from the LFP signals are affected under different paradigms of stimulation on/off. We first study the notion of beta power suppression in LFP signals under different scenarios (stimulation on/off and medication on/off). Afterward, we explore the accuracy of support vector machines in predicting human actions (button press and reach) using the spectrogram of STN-LFP signals. Our experiments on the recorded LFP signals of three subjects confirm that the beta power is suppressed significantly when the patients take medication (p-value<0.002) or stimulation (p-value<0.0003). The results also show that we can classify different behaviors with a reasonable accuracy of 85% even when the high-amplitude stimulation is applied.
Tasks
Published	2018-04-09
URL	http://arxiv.org/abs/1804.03190v1
PDF	http://arxiv.org/pdf/1804.03190v1.pdf
PWC	https://paperswithcode.com/paper/studying-the-effects-of-deep-brain
Repo
Framework

Staff line Removal using Generative Adversarial Networks


Title	Staff line Removal using Generative Adversarial Networks
Authors	Aishik Konwer, Ayan Kumar Bhunia, Abir Bhowmick, Ankan Kumar Bhunia, Prithaj Banerjee, Partha Pratim Roy, Umapada Pal
Abstract	Staff line removal is a crucial pre-processing step in Optical Music Recognition. It is a challenging task to simultaneously reduce the noise and also retain the quality of music symbol context in ancient degraded music score images. In this paper we propose a novel approach for staff line removal, based on Generative Adversarial Networks. We convert staff line images into patches and feed them into a U-Net, used as Generator. The Generator intends to produce staff-less images at the output. Then the Discriminator does binary classification and differentiates between the generated fake staff-less image and real ground truth staff less image. For training, we use a Loss function which is a weighted combination of L2 loss and Adversarial loss. L2 loss minimizes the difference between real and fake staff-less image. Adversarial loss helps to retrieve more high quality textures in generated images. Thus our architecture supports solutions which are closer to ground truth and it reflects in our results. For evaluation we consider the ICDAR/GREC 2013 staff removal database. Our method achieves superior performance in comparison to other conventional approaches.
Tasks
Published	2018-01-22
URL	http://arxiv.org/abs/1801.07141v3
PDF	http://arxiv.org/pdf/1801.07141v3.pdf
PWC	https://paperswithcode.com/paper/staff-line-removal-using-generative
Repo
Framework

Recent Progress on Graph Partitioning Problems Using Evolutionary Computation


Title	Recent Progress on Graph Partitioning Problems Using Evolutionary Computation
Authors	Hye-Jin Kim, Yong-Hyuk Kim
Abstract	The graph partitioning problem (GPP) is a representative combinatorial optimization problem which is NP-hard. Currently, various approaches to solve GPP have been introduced. Among these, the GPP solution using evolutionary computation (EC) is an effective approach. There has not been any survey on the research applying EC to GPP since 2011. In this survey, we introduce various attempts to apply EC to GPP made in the recent seven years.
Tasks	Combinatorial Optimization, graph partitioning
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01623v1
PDF	http://arxiv.org/pdf/1805.01623v1.pdf
PWC	https://paperswithcode.com/paper/recent-progress-on-graph-partitioning
Repo
Framework

Joint Neural Entity Disambiguation with Output Space Search


Title	Joint Neural Entity Disambiguation with Output Space Search
Authors	Hamed Shahbazi, Xiaoli Z. Fern, Reza Ghaeini, Chao Ma, Rasha Obeidat, Prasad Tadepalli
Abstract	In this paper, we present a novel model for entity disambiguation that combines both local contextual information and global evidences through Limited Discrepancy Search (LDS). Given an input document, we start from a complete solution constructed by a local model and conduct a search in the space of possible corrections to improve the local solution from a global view point. Our search utilizes a heuristic function to focus more on the least confident local decisions and a pruning function to score the global solutions based on their local fitness and the global coherences among the predicted entities. Experimental results on CoNLL 2003 and TAC 2010 benchmarks verify the effectiveness of our model.
Tasks	Entity Disambiguation
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07495v1
PDF	http://arxiv.org/pdf/1806.07495v1.pdf
PWC	https://paperswithcode.com/paper/joint-neural-entity-disambiguation-with
Repo
Framework

English-Catalan Neural Machine Translation in the Biomedical Domain through the cascade approach


Title	English-Catalan Neural Machine Translation in the Biomedical Domain through the cascade approach
Authors	Marta R. Costa-jussà, Noe Casas, Maite Melero
Abstract	This paper describes the methodology followed to build a neural machine translation system in the biomedical domain for the English-Catalan language pair. This task can be considered a low-resourced task from the point of view of the domain and the language pair. To face this task, this paper reports experiments on a cascade pivot strategy through Spanish for the neural machine translation using the English-Spanish SCIELO and Spanish-Catalan El Peri'odico database. To test the final performance of the system, we have created a new test data set for English-Catalan in the biomedical domain which is freely available on request.
Tasks	Machine Translation
Published	2018-03-19
URL	http://arxiv.org/abs/1803.07139v2
PDF	http://arxiv.org/pdf/1803.07139v2.pdf
PWC	https://paperswithcode.com/paper/english-catalan-neural-machine-translation-in
Repo
Framework

A Distributed Reinforcement Learning Solution With Knowledge Transfer Capability for A Bike Rebalancing Problem


Title	A Distributed Reinforcement Learning Solution With Knowledge Transfer Capability for A Bike Rebalancing Problem
Authors	Ian Xiao
Abstract	Rebalancing is a critical service bottleneck for many transportation services, such as Citi Bike. Citi Bike relies on manual orchestrations of rebalancing bikes between dispatchers and field agents. Motivated by such problem and the lack of smart autonomous solutions in this area, this project explored a new RL architecture called Distributed RL (DiRL) with Transfer Learning (TL) capability. The DiRL solution is adaptive to changing traffic dynamics when keeping bike stock under control at the minimum cost. DiRL achieved a 350% improvement in bike rebalancing autonomously and TL offered a 62.4% performance boost in managing an entire bike network. Lastly, a field trip to the dispatch office of Chariot, a ride-sharing service, provided insights to overcome challenges of deploying an RL solution in the real world.
Tasks	Transfer Learning
Published	2018-10-09
URL	http://arxiv.org/abs/1810.04058v1
PDF	http://arxiv.org/pdf/1810.04058v1.pdf
PWC	https://paperswithcode.com/paper/a-distributed-reinforcement-learning-solution
Repo
Framework

An Overview of Datatype Quantization Techniques for Convolutional Neural Networks


Title	An Overview of Datatype Quantization Techniques for Convolutional Neural Networks
Authors	Ali Athar
Abstract	Convolutional Neural Networks (CNNs) are becoming increasingly popular due to their superior performance in the domain of computer vision, in applications such as objection detection and recognition. However, they demand complex, power-consuming hardware which makes them unsuitable for implementation on low-power mobile and embedded devices. In this paper, a description and comparison of various techniques is presented which aim to mitigate this problem. This is primarily achieved by quantizing the floating-point weights and activations to reduce the hardware requirements, and adapting the training and inference algorithms to maintain the network’s performance.
Tasks	Quantization
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07530v1
PDF	http://arxiv.org/pdf/1808.07530v1.pdf
PWC	https://paperswithcode.com/paper/an-overview-of-datatype-quantization
Repo
Framework

Early Prediction of Acute Kidney Injury in Critical Care Setting Using Clinical Notes


Title	Early Prediction of Acute Kidney Injury in Critical Care Setting Using Clinical Notes
Authors	Yikuan Li, Liang Yao, Chengsheng Mao, Anand Srivastava, Xiaoqian Jiang, Yuan Luo
Abstract	Acute kidney injury (AKI) in critically ill patients is associated with significant morbidity and mortality. Development of novel methods to identify patients with AKI earlier will allow for testing of novel strategies to prevent or reduce the complications of AKI. We developed data-driven prediction models to estimate the risk of new AKI onset. We generated models from clinical notes within the first 24 hours following intensive care unit (ICU) admission extracted from Medical Information Mart for Intensive Care III (MIMIC-III). From the clinical notes, we generated clinically meaningful word and concept representations and embeddings, respectively. Five supervised learning classifiers and knowledge-guided deep learning architecture were used to construct prediction models. The best configuration yielded a competitive AUC of 0.779. Our work suggests that natural language processing of clinical notes can be applied to assist clinicians in identifying the risk of incident AKI onset in critically ill patients upon admission to the ICU.
Tasks
Published	2018-11-07
URL	http://arxiv.org/abs/1811.02757v2
PDF	http://arxiv.org/pdf/1811.02757v2.pdf
PWC	https://paperswithcode.com/paper/early-prediction-of-acute-kidney-injury-in
Repo
Framework

SegDenseNet: Iris Segmentation for Pre and Post Cataract Surgery


Title	SegDenseNet: Iris Segmentation for Pre and Post Cataract Surgery
Authors	Aditya Lakra, Pavani Tripathi, Rohit Keshari, Mayank Vatsa, Richa Singh
Abstract	Cataract is caused due to various factors such as age, trauma, genetics, smoking and substance consumption, and radiation. It is one of the major common ophthalmic diseases worldwide which can potentially affect iris-based biometric systems. India, which hosts the largest biometrics project in the world, has about 8 million people undergoing cataract surgery annually. While existing research shows that cataract does not have a major impact on iris recognition, our observations suggest that the iris segmentation approaches are not well equipped to handle cataract or post cataract surgery cases. Therefore, failure in iris segmentation affects the overall recognition performance. This paper presents an efficient iris segmentation algorithm with variations due to cataract and post cataract surgery. The proposed algorithm, termed as SegDenseNet, is a deep learning algorithm based on DenseNets. The experiments on the IIITD Cataract database show that improving the segmentation enhances the identification by up to 25% across different sensors and matchers.
Tasks	Iris Recognition, Iris Segmentation
Published	2018-01-30
URL	http://arxiv.org/abs/1801.10100v2
PDF	http://arxiv.org/pdf/1801.10100v2.pdf
PWC	https://paperswithcode.com/paper/segdensenet-iris-segmentation-for-pre-and
Repo
Framework

Estimation of lactate threshold with machine learning techniques in recreational runners


Title	Estimation of lactate threshold with machine learning techniques in recreational runners
Authors	Urtats Etxegarai, Eva Portillo, Jon Irazusta, Ander Arriandiaga, Itziar Cabanes
Abstract	Lactate threshold is considered an essential parameter when assessing performance of elite and recreational runners and prescribing training intensities in endurance sports. However, the measurement of blood lactate concentration requires expensive equipment and the extraction of blood samples, which are inconvenient for frequent monitoring. Furthermore, most recreational runners do not have access to routine assessment of their physical fitness by the aforementioned equipment so they are not able to calculate the lactate threshold without resorting to an expensive and specialized centre. Therefore, the main objective of this study is to create an intelligent system capable of estimating the lactate threshold of recreational athletes participating in endurance running sports. The solution here proposed is based on a machine learning system which models the lactate evolution using recurrent neural networks and includes the proposal of standardization of the temporal axis as well as a modification of the stratified sampling method. The results show that the proposed system accurately estimates the lactate threshold of 89.52% of the athletes and its correlation with the experimentally measured lactate threshold is very high (R=0,89). Moreover, its behaviour with the test dataset is as good as with the training set, meaning that the generalization power of the model is high. Therefore, in this study a machine learning based system is proposed as alternative to the traditional invasive lactate threshold measurement tests for recreational runners.
Tasks
Published	2018-03-15
URL	http://arxiv.org/abs/1803.06030v2
PDF	http://arxiv.org/pdf/1803.06030v2.pdf
PWC	https://paperswithcode.com/paper/estimation-of-lactate-threshold-with-machine
Repo
Framework

DATELINE: Deep Plackett-Luce Model with Uncertainty Measurements


Title	DATELINE: Deep Plackett-Luce Model with Uncertainty Measurements
Authors	Bo Han
Abstract	The aggregation of k-ary preferences is a historical and important problem, since it has many real-world applications, such as peer grading, presidential elections and restaurant ranking. Meanwhile, variants of Plackett-Luce model has been applied to aggregate k-ary preferences. However, there are two urgent issues still existing in the current variants. First, most of them ignore feature information. Namely, they consider k-ary preferences instead of instance-dependent k-ary preferences. Second, these variants barely consider the uncertainty in k-ary preferences provided by agnostic crowds. In this paper, we propose Deep plAckeTt-luce modEL wIth uNcertainty mEasurements (DATELINE), which can address both issues simultaneously. To address the first issue, we employ deep neural networks mapping each instance into its ranking score in Plackett-Luce model. Then, we present a weighted Plackett-Luce model to solve the second issue, where the weight is a dynamic uncertainty vector measuring the worker quality. More importantly, we provide theoretical guarantees for DATELINE to justify its robustness.
Tasks
Published	2018-12-14
URL	http://arxiv.org/abs/1812.05877v1
PDF	http://arxiv.org/pdf/1812.05877v1.pdf
PWC	https://paperswithcode.com/paper/dateline-deep-plackett-luce-model-with
Repo
Framework

ChatPainter: Improving Text to Image Generation using Dialogue


Title	ChatPainter: Improving Text to Image Generation using Dialogue
Authors	Shikhar Sharma, Dendi Suhubdy, Vincent Michalski, Samira Ebrahimi Kahou, Yoshua Bengio
Abstract	Synthesizing realistic images from text descriptions on a dataset like Microsoft Common Objects in Context (MS COCO), where each image can contain several objects, is a challenging task. Prior work has used text captions to generate images. However, captions might not be informative enough to capture the entire image and insufficient for the model to be able to understand which objects in the images correspond to which words in the captions. We show that adding a dialogue that further describes the scene leads to significant improvement in the inception score and in the quality of generated images on the MS COCO dataset.
Tasks	Image Generation, Text-to-Image Generation
Published	2018-02-22
URL	http://arxiv.org/abs/1802.08216v1
PDF	http://arxiv.org/pdf/1802.08216v1.pdf
PWC	https://paperswithcode.com/paper/chatpainter-improving-text-to-image
Repo
Framework

Privacy-Preserving Distributed Deep Learning for Clinical Data


Title	Privacy-Preserving Distributed Deep Learning for Clinical Data
Authors	Brett K. Beaulieu-Jones, William Yuan, Samuel G. Finlayson, Zhiwei Steven Wu
Abstract	Deep learning with medical data often requires larger samples sizes than are available at single providers. While data sharing among institutions is desirable to train more accurate and sophisticated models, it can lead to severe privacy concerns due the sensitive nature of the data. This problem has motivated a number of studies on distributed training of neural networks that do not require direct sharing of the training data. However, simple distributed training does not offer provable privacy guarantees to satisfy technical safe standards and may reveal information about the underlying patients. We present a method to train neural networks for clinical data in a distributed fashion under differential privacy. We demonstrate these methods on two datasets that include information from multiple independent sites, the eICU collaborative Research Database and The Cancer Genome Atlas.
Tasks
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01484v1
PDF	http://arxiv.org/pdf/1812.01484v1.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-distributed-deep-learning
Repo
Framework

Continual Reinforcement Learning with Complex Synapses


Title	Continual Reinforcement Learning with Complex Synapses
Authors	Christos Kaplanis, Murray Shanahan, Claudia Clopath
Abstract	Unlike humans, who are capable of continual learning over their lifetimes, artificial neural networks have long been known to suffer from a phenomenon known as catastrophic forgetting, whereby new learning can lead to abrupt erasure of previously acquired knowledge. Whereas in a neural network the parameters are typically modelled as scalar values, an individual synapse in the brain comprises a complex network of interacting biochemical components that evolve at different timescales. In this paper, we show that by equipping tabular and deep reinforcement learning agents with a synaptic model that incorporates this biological complexity (Benna & Fusi, 2016), catastrophic forgetting can be mitigated at multiple timescales. In particular, we find that as well as enabling continual learning across sequential training of two simple tasks, it can also be used to overcome within-task forgetting by reducing the need for an experience replay database.
Tasks	Continual Learning
Published	2018-02-20
URL	http://arxiv.org/abs/1802.07239v2
PDF	http://arxiv.org/pdf/1802.07239v2.pdf
PWC	https://paperswithcode.com/paper/continual-reinforcement-learning-with-complex
Repo
Framework

Dual Principal Component Pursuit: Probability Analysis and Efficient Algorithms


Title	Dual Principal Component Pursuit: Probability Analysis and Efficient Algorithms
Authors	Zhihui Zhu, Yifan Wang, Daniel P. Robinson, Daniel Q. Naiman, Rene Vidal, Manolis C. Tsakiris
Abstract	Recent methods for learning a linear subspace from data corrupted by outliers are based on convex $\ell_1$ and nuclear norm optimization and require the dimension of the subspace and the number of outliers to be sufficiently small. In sharp contrast, the recently proposed Dual Principal Component Pursuit (DPCP) method can provably handle subspaces of high dimension by solving a non-convex $\ell_1$ optimization problem on the sphere. However, its geometric analysis is based on quantities that are difficult to interpret and are not amenable to statistical analysis. In this paper we provide a refined geometric analysis and a new statistical analysis that show that DPCP can tolerate as many outliers as the square of the number of inliers, thus improving upon other provably correct robust PCA methods. We also propose a scalable Projected Sub-Gradient Method method (DPCP-PSGM) for solving the DPCP problem and show it admits linear convergence even though the underlying optimization problem is non-convex and non-smooth. Experiments on road plane detection from 3D point cloud data demonstrate that DPCP-PSGM can be more efficient than the traditional RANSAC algorithm, which is one of the most popular methods for such computer vision applications.
Tasks
Published	2018-12-24
URL	http://arxiv.org/abs/1812.09924v1
PDF	http://arxiv.org/pdf/1812.09924v1.pdf
PWC	https://paperswithcode.com/paper/dual-principal-component-pursuit-probability
Repo
Framework