July 27, 2019

2924 words 14 mins read

Paper Group ANR 516

Fast Resampling of 3D Point Clouds via Graphs. Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data. Reprogramming Matter, Life, and Purpose. Interpatient Respiratory Motion Model Transfer for Virtual Reality Simulations of Liver Punctures. Look-ahead Attention for Generation in Neural M …

Fast Resampling of 3D Point Clouds via Graphs


Title	Fast Resampling of 3D Point Clouds via Graphs
Authors	Siheng Chen, Dong Tian, Chen Feng, Anthony Vetro, Jelena Kovačević
Abstract	To reduce cost in storing, processing and visualizing a large-scale point cloud, we consider a randomized resampling strategy to select a representative subset of points while preserving application-dependent features. The proposed strategy is based on graphs, which can represent underlying surfaces and lend themselves well to efficient computation. We use a general feature-extraction operator to represent application-dependent features and propose a general reconstruction error to evaluate the quality of resampling. We obtain a general form of optimal resampling distribution by minimizing the reconstruction error. The proposed optimal resampling distribution is guaranteed to be shift, rotation and scale-invariant in the 3D space. We next specify the feature-extraction operator to be a graph filter and study specific resampling strategies based on all-pass, low-pass, high-pass graph filtering and graph filter banks. We finally apply the proposed methods to three applications: large-scale visualization, accurate registration and robust shape modeling. The empirical performance validates the effectiveness and efficiency of the proposed resampling methods.
Tasks
Published	2017-02-11
URL	http://arxiv.org/abs/1702.06397v1
PDF	http://arxiv.org/pdf/1702.06397v1.pdf
PWC	https://paperswithcode.com/paper/fast-resampling-of-3d-point-clouds-via-graphs
Repo
Framework

Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data


Title	Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
Authors	Daniel George, E. A. Huerta
Abstract	The recent Nobel-prize-winning detections of gravitational waves from merging black holes and the subsequent detection of the collision of two neutron stars in coincidence with electromagnetic observations have inaugurated a new era of multimessenger astrophysics. To enhance the scope of this emergent field of science, we pioneered the use of deep learning with convolutional neural networks, that take time-series inputs, for rapid detection and characterization of gravitational wave signals. This approach, Deep Filtering, was initially demonstrated using simulated LIGO noise. In this article, we present the extension of Deep Filtering using real data from LIGO, for both detection and parameter estimation of gravitational waves from binary black hole mergers using continuous data streams from multiple LIGO detectors. We demonstrate for the first time that machine learning can detect and estimate the true parameters of real events observed by LIGO. Our results show that Deep Filtering achieves similar sensitivities and lower errors compared to matched-filtering while being far more computationally efficient and more resilient to glitches, allowing real-time processing of weak time-series signals in non-stationary non-Gaussian noise with minimal resources, and also enables the detection of new classes of gravitational wave sources that may go unnoticed with existing detection algorithms. This unified framework for data analysis is ideally suited to enable coincident detection campaigns of gravitational waves and their multimessenger counterparts in real-time.
Tasks	Gravitational Wave Detection, Time Series
Published	2017-11-08
URL	http://arxiv.org/abs/1711.03121v1
PDF	http://arxiv.org/pdf/1711.03121v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-real-time-gravitational-1
Repo
Framework

Reprogramming Matter, Life, and Purpose


Title	Reprogramming Matter, Life, and Purpose
Authors	Hector Zenil
Abstract	Reprogramming matter may sound far-fetched, but we have been doing it with increasing power and staggering efficiency for at least 60 years, and for centuries we have been paving the way toward the ultimate reprogrammed fate of the universe, the vessel of all programs. How will we be doing it in 60 years’ time and how will it impact life and the purpose both of machines and of humans?
Tasks
Published	2017-04-02
URL	http://arxiv.org/abs/1704.00725v4
PDF	http://arxiv.org/pdf/1704.00725v4.pdf
PWC	https://paperswithcode.com/paper/reprogramming-matter-life-and-purpose
Repo
Framework

Interpatient Respiratory Motion Model Transfer for Virtual Reality Simulations of Liver Punctures


Title	Interpatient Respiratory Motion Model Transfer for Virtual Reality Simulations of Liver Punctures
Authors	Andre Mastmeyer, Matthias Wilms, Heinz Handels
Abstract	Current virtual reality (VR) training simulators of liver punctures often rely on static 3D patient data and use an unrealistic (sinusoidal) periodic animation of the respiratory movement. Existing methods for the animation of breathing motion support simple mathematical or patient-specific, estimated breathing models. However with personalized breathing models for each new patient, a heavily dose relevant or expensive 4D data acquisition is mandatory for keyframe-based motion modeling. Given the reference 4D data, first a model building stage using linear regression motion field modeling takes place. Then the methodology shown here allows the transfer of existing reference respiratory motion models of a 4D reference patient to a new static 3D patient. This goal is achieved by using non-linear inter-patient registration to warp one personalized 4D motion field model to new 3D patient data. This cost- and dose-saving new method is shown here visually in a qualitative proof-of-concept study.
Tasks
Published	2017-07-26
URL	http://arxiv.org/abs/1707.08554v2
PDF	http://arxiv.org/pdf/1707.08554v2.pdf
PWC	https://paperswithcode.com/paper/interpatient-respiratory-motion-model
Repo
Framework

Look-ahead Attention for Generation in Neural Machine Translation


Title	Look-ahead Attention for Generation in Neural Machine Translation
Authors	Long Zhou, Jiajun Zhang, Chengqing Zong
Abstract	The attention model has become a standard component in neural machine translation (NMT) and it guides translation process by selectively focusing on parts of the source sentence when predicting each target word. However, we find that the generation of a target word does not only depend on the source sentence, but also rely heavily on the previous generated target words, especially the distant words which are difficult to model by using recurrent neural networks. To solve this problem, we propose in this paper a novel look-ahead attention mechanism for generation in NMT, which aims at directly capturing the dependency relationship between target words. We further design three patterns to integrate our look-ahead attention into the conventional attention model. Experiments on NIST Chinese-to-English and WMT English-to-German translation tasks show that our proposed look-ahead attention mechanism achieves substantial improvements over state-of-the-art baselines.
Tasks	Machine Translation
Published	2017-08-30
URL	http://arxiv.org/abs/1708.09217v1
PDF	http://arxiv.org/pdf/1708.09217v1.pdf
PWC	https://paperswithcode.com/paper/look-ahead-attention-for-generation-in-neural
Repo
Framework

Scene learning, recognition and similarity detection in a fuzzy ontology via human examples


Title	Scene learning, recognition and similarity detection in a fuzzy ontology via human examples
Authors	Luca Buoncompagni, Fulvio Mastrogiovanni, Alessandro Saffiotti
Abstract	This paper introduces a Fuzzy Logic framework for scene learning, recognition and similarity detection, where scenes are taught via human examples. The framework allows a robot to: (i) deal with the intrinsic vagueness associated with determining spatial relations among objects; (ii) infer similarities and dissimilarities in a set of scenes, and represent them in a hierarchical structure represented in a Fuzzy ontology. In this paper, we briefly formalize our approach and we provide a few use cases by way of illustration. Nevertheless, we discuss how the framework can be used in real-world scenarios.
Tasks
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09433v1
PDF	http://arxiv.org/pdf/1709.09433v1.pdf
PWC	https://paperswithcode.com/paper/scene-learning-recognition-and-similarity
Repo
Framework

Semi-supervised Multimodal Hashing


Title	Semi-supervised Multimodal Hashing
Authors	Dayong Tian, Maoguo Gong, Deyun Zhou, Jiao Shi, Yu Lei
Abstract	Retrieving nearest neighbors across correlated data in multiple modalities, such as image-text pairs on Facebook and video-tag pairs on YouTube, has become a challenging task due to the huge amount of data. Multimodal hashing methods that embed data into binary codes can boost the retrieving speed and reduce storage requirement. As unsupervised multimodal hashing methods are usually inferior to supervised ones, while the supervised ones requires too much manually labeled data, the proposed method in this paper utilizes a part of labels to design a semi-supervised multimodal hashing method. It first computes the transformation matrices for data matrices and label matrix. Then, with these transformation matrices, fuzzy logic is introduced to estimate a label matrix for unlabeled data. Finally, it uses the estimated label matrix to learn hashing functions for data in each modality to generate a unified binary code matrix. Experiments show that the proposed semi-supervised method with 50% labels can get a medium performance among the compared supervised ones and achieve an approximate performance to the best supervised method with 90% labels. With only 10% labels, the proposed method can still compete with the worst compared supervised one.
Tasks
Published	2017-12-09
URL	https://arxiv.org/abs/1712.03404v1
PDF	https://arxiv.org/pdf/1712.03404v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-multimodal-hashing
Repo
Framework

Performance Comparison of Intrusion Detection Systems and Application of Machine Learning to Snort System


Title	Performance Comparison of Intrusion Detection Systems and Application of Machine Learning to Snort System
Authors	Syed Ali Raza Shah, Biju Issac
Abstract	This study investigates the performance of two open source intrusion detection systems (IDSs) namely Snort and Suricata for accurately detecting the malicious traffic on computer networks. Snort and Suricata were installed on two different but identical computers and the performance was evaluated at 10 Gbps network speed. It was noted that Suricata could process a higher speed of network traffic than Snort with lower packet drop rate but it consumed higher computational resources. Snort had higher detection accuracy and was thus selected for further experiments. It was observed that the Snort triggered a high rate of false positive alarms. To solve this problem a Snort adaptive plug-in was developed. To select the best performing algorithm for Snort adaptive plug-in, an empirical study was carried out with different learning algorithms and Support Vector Machine (SVM) was selected. A hybrid version of SVM and Fuzzy logic produced a better detection accuracy. But the best result was achieved using an optimised SVM with firefly algorithm with FPR (false positive rate) as 8.6% and FNR (false negative rate) as 2.2%, which is a good result. The novelty of this work is the performance comparison of two IDSs at 10 Gbps and the application of hybrid and optimised machine learning algorithms to Snort.
Tasks	Intrusion Detection
Published	2017-10-13
URL	http://arxiv.org/abs/1710.04843v2
PDF	http://arxiv.org/pdf/1710.04843v2.pdf
PWC	https://paperswithcode.com/paper/performance-comparison-of-intrusion-detection
Repo
Framework

TANKER: Distributed Architecture for Named Entity Recognition and Disambiguation


Title	TANKER: Distributed Architecture for Named Entity Recognition and Disambiguation
Authors	Sandro A. Coelho, Diego Moussallem, Gustavo C. Publio, Diego Esteves
Abstract	Named Entity Recognition and Disambiguation (NERD) systems have recently been widely researched to deal with the significant growth of the Web. NERD systems are crucial for several Natural Language Processing (NLP) tasks such as summarization, understanding, and machine translation. However, there is no standard interface specification, i.e. these systems may vary significantly either for exporting their outputs or for processing the inputs. Thus, when a given company desires to implement more than one NERD system, the process is quite exhaustive and prone to failure. In addition, industrial solutions demand critical requirements, e.g., large-scale processing, completeness, versatility, and licenses. Commonly, these requirements impose a limitation, making good NERD models to be ignored by companies. This paper presents TANKER, a distributed architecture which aims to overcome scalability, reliability and failure tolerance limitations related to industrial needs by combining NERD systems. To this end, TANKER relies on a micro-services oriented architecture, which enables agile development and delivery of complex enterprise applications. In addition, TANKER provides a standardized API which makes possible to combine several NERD systems at once.
Tasks	Machine Translation, Named Entity Recognition
Published	2017-08-30
URL	http://arxiv.org/abs/1708.09230v3
PDF	http://arxiv.org/pdf/1708.09230v3.pdf
PWC	https://paperswithcode.com/paper/tanker-distributed-architecture-for-named
Repo
Framework

Self corrective Perturbations for Semantic Segmentation and Classification


Title	Self corrective Perturbations for Semantic Segmentation and Classification
Authors	Swami Sankaranarayanan, Arpit Jain, Ser Nam Lim
Abstract	Convolutional Neural Networks have been a subject of great importance over the past decade and great strides have been made in their utility for producing state of the art performance in many computer vision problems. However, the behavior of deep networks is yet to be fully understood and is still an active area of research. In this work, we present an intriguing behavior: pre-trained CNNs can be made to improve their predictions by structurally perturbing the input. We observe that these perturbations - referred as Guided Perturbations - enable a trained network to improve its prediction performance without any learning or change in network weights. We perform various ablative experiments to understand how these perturbations affect the local context and feature representations. Furthermore, we demonstrate that this idea can improve performance of several existing approaches on semantic segmentation and scene labeling tasks on the PASCAL VOC dataset and supervised classification tasks on MNIST and CIFAR10 datasets.
Tasks	Scene Labeling, Semantic Segmentation
Published	2017-03-23
URL	http://arxiv.org/abs/1703.07928v2
PDF	http://arxiv.org/pdf/1703.07928v2.pdf
PWC	https://paperswithcode.com/paper/self-corrective-perturbations-for-semantic
Repo
Framework

A Low Dimensionality Representation for Language Variety Identification


Title	A Low Dimensionality Representation for Language Variety Identification
Authors	Francisco Rangel, Marc Franco-Salvador, Paolo Rosso
Abstract	Language variety identification aims at labelling texts in a native language (e.g. Spanish, Portuguese, English) with its specific variation (e.g. Argentina, Chile, Mexico, Peru, Spain; Brazil, Portugal; UK, US). In this work we propose a low dimensionality representation (LDR) to address this task with five different varieties of Spanish: Argentina, Chile, Mexico, Peru and Spain. We compare our LDR method with common state-of-the-art representations and show an increase in accuracy of ~35%. Furthermore, we compare LDR with two reference distributed representation models. Experimental results show competitive performance while dramatically reducing the dimensionality –and increasing the big data suitability– to only 6 features per variety. Additionally, we analyse the behaviour of the employed machine learning algorithms and the most discriminating features. Finally, we employ an alternative dataset to test the robustness of our low dimensionality representation with another set of similar languages.
Tasks
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10754v1
PDF	http://arxiv.org/pdf/1705.10754v1.pdf
PWC	https://paperswithcode.com/paper/a-low-dimensionality-representation-for
Repo
Framework

On Generalized Bellman Equations and Temporal-Difference Learning


Title	On Generalized Bellman Equations and Temporal-Difference Learning
Authors	Huizhen Yu, A. Rupam Mahmood, Richard S. Sutton
Abstract	We consider off-policy temporal-difference (TD) learning in discounted Markov decision processes, where the goal is to evaluate a policy in a model-free way by using observations of a state process generated without executing the policy. To curb the high variance issue in off-policy TD learning, we propose a new scheme of setting the $\lambda$-parameters of TD, based on generalized Bellman equations. Our scheme is to set $\lambda$ according to the eligibility trace iterates calculated in TD, thereby easily keeping these traces in a desired bounded range. Compared with prior work, this scheme is more direct and flexible, and allows much larger $\lambda$ values for off-policy TD learning with bounded traces. As to its soundness, using Markov chain theory, we prove the ergodicity of the joint state-trace process under nonrestrictive conditions, and we show that associated with our scheme is a generalized Bellman equation (for the policy to be evaluated) that depends on both the evolution of $\lambda$ and the unique invariant probability measure of the state-trace process. These results not only lead immediately to a characterization of the convergence behavior of least-squares based implementation of our scheme, but also prepare the ground for further analysis of gradient-based implementations.
Tasks
Published	2017-04-14
URL	http://arxiv.org/abs/1704.04463v2
PDF	http://arxiv.org/pdf/1704.04463v2.pdf
PWC	https://paperswithcode.com/paper/on-generalized-bellman-equations-and-temporal
Repo
Framework

Learning Light Transport the Reinforced Way


Title	Learning Light Transport the Reinforced Way
Authors	Ken Dahm, Alexander Keller
Abstract	We show that the equations of reinforcement learning and light transport simulation are related integral equations. Based on this correspondence, a scheme to learn importance while sampling path space is derived. The new approach is demonstrated in a consistent light transport simulation algorithm that uses reinforcement learning to progressively learn where light comes from. As using this information for importance sampling includes information about visibility, too, the number of light transport paths with zero contribution is dramatically reduced, resulting in much less noisy images within a fixed time budget.
Tasks
Published	2017-01-25
URL	http://arxiv.org/abs/1701.07403v2
PDF	http://arxiv.org/pdf/1701.07403v2.pdf
PWC	https://paperswithcode.com/paper/learning-light-transport-the-reinforced-way
Repo
Framework

Fighting with the Sparsity of Synonymy Dictionaries


Title	Fighting with the Sparsity of Synonymy Dictionaries
Authors	Dmitry Ustalov, Mikhail Chernoskutov, Chris Biemann, Alexander Panchenko
Abstract	Graph-based synset induction methods, such as MaxMax and Watset, induce synsets by performing a global clustering of a synonymy graph. However, such methods are sensitive to the structure of the input synonymy graph: sparseness of the input dictionary can substantially reduce the quality of the extracted synsets. In this paper, we propose two different approaches designed to alleviate the incompleteness of the input dictionaries. The first one performs a pre-processing of the graph by adding missing edges, while the second one performs a post-processing by merging similar synset clusters. We evaluate these approaches on two datasets for the Russian language and discuss their impact on the performance of synset induction methods. Finally, we perform an extensive error analysis of each approach and discuss prominent alternative methods for coping with the problem of the sparsity of the synonymy dictionaries.
Tasks
Published	2017-08-30
URL	http://arxiv.org/abs/1708.09234v1
PDF	http://arxiv.org/pdf/1708.09234v1.pdf
PWC	https://paperswithcode.com/paper/fighting-with-the-sparsity-of-synonymy
Repo
Framework

A Hypercat-enabled Semantic Internet of Things Data Hub: Technical Report


Title	A Hypercat-enabled Semantic Internet of Things Data Hub: Technical Report
Authors	Ilias Tachmazidis, Sotiris Batsakis, John Davies, Alistair Duke, Mauro Vallati, Grigoris Antoniou, Sandra Stincic Clarke
Abstract	An increasing amount of information is generated from the rapidly increasing number of sensor networks and smart devices. A wide variety of sources generate and publish information in different formats, thus highlighting interoperability as one of the key prerequisites for the success of Internet of Things (IoT). The BT Hypercat Data Hub provides a focal point for the sharing and consumption of available datasets from a wide range of sources. In this work, we propose a semantic enrichment of the BT Hypercat Data Hub, using well-accepted Semantic Web standards and tools. We propose an ontology that captures the semantics of the imported data and present the BT SPARQL Endpoint by means of a mapping between SPARQL and SQL queries. Furthermore, federated SPARQL queries allow queries over multiple hub-based and external data sources. Finally, we provide two use cases in order to illustrate the advantages afforded by our semantic approach.
Tasks
Published	2017-03-01
URL	http://arxiv.org/abs/1703.00391v2
PDF	http://arxiv.org/pdf/1703.00391v2.pdf
PWC	https://paperswithcode.com/paper/a-hypercat-enabled-semantic-internet-of
Repo
Framework