October 19, 2019

2977 words 14 mins read

Paper Group ANR 364

Subspace Support Vector Data Description. A Non-parametric Multi-stage Learning Framework for Cognitive Spectrum Access in IoT Networks. Microsoft’s Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data. Identifying emergency stages in Facebook posts of police departments with convolutional and recurrent …

Subspace Support Vector Data Description


Title	Subspace Support Vector Data Description
Authors	Fahad Sohrab, Jenni Raitoharju, Moncef Gabbouj, Alexandros Iosifidis
Abstract	This paper proposes a novel method for solving one-class classification problems. The proposed approach, namely Subspace Support Vector Data Description, maps the data to a subspace that is optimized for one-class classification. In that feature space, the optimal hypersphere enclosing the target class is then determined. The method iteratively optimizes the data mapping along with data description in order to define a compact class representation in a low-dimensional feature space. We provide both linear and non-linear mappings for the proposed method. Experiments on 14 publicly available datasets indicate that the proposed Subspace Support Vector Data Description provides better performance compared to baselines and other recently proposed one-class classification methods.
Tasks
Published	2018-02-12
URL	http://arxiv.org/abs/1802.03989v3
PDF	http://arxiv.org/pdf/1802.03989v3.pdf
PWC	https://paperswithcode.com/paper/subspace-support-vector-data-description
Repo
Framework

A Non-parametric Multi-stage Learning Framework for Cognitive Spectrum Access in IoT Networks


Title	A Non-parametric Multi-stage Learning Framework for Cognitive Spectrum Access in IoT Networks
Authors	Thulasi Tholeti, Vishnu Raj, Sheetal Kalyani
Abstract	Given the increasing number of devices that is going to get connected to wireless networks with the advent of Internet of Things, spectrum scarcity will present a major challenge. Application of opportunistic spectrum access mechanisms to IoT networks will become increasingly important to solve this. In this paper, we present a cognitive radio network architecture which uses multi-stage online learning techniques for spectrum assignment to devices, with the aim of improving the throughput and energy efficiency of the IoT devices. In the first stage, we use an AI technique to learn the quality of a user-channel pairing. The next stage utilizes a non-parametric Bayesian learning algorithm to estimate the Primary User OFF time in each channel. The third stage augments the Bayesian learner with implicit exploration to accelerate the learning procedure. The proposed method leads to significant improvement in throughput and energy efficiency of the IoT devices while keeping the interference to the primary users minimal. We provide comprehensive empirical validation of the method with other learning based approaches.
Tasks
Published	2018-04-30
URL	http://arxiv.org/abs/1804.11135v1
PDF	http://arxiv.org/pdf/1804.11135v1.pdf
PWC	https://paperswithcode.com/paper/a-non-parametric-multi-stage-learning
Repo
Framework

Microsoft’s Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data


Title	Microsoft’s Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data
Authors	Marcin Junczys-Dowmunt
Abstract	This paper describes the Microsoft submission to the WMT2018 news translation shared task. We participated in one language direction – English-German. Our system follows current best-practice and combines state-of-the-art models with new data filtering (dual conditional cross-entropy filtering) and sentence weighting methods. We trained fairly standard Transformer-big models with an updated version of Edinburgh’s training scheme for WMT2017 and experimented with different filtering schemes for Paracrawl. According to automatic metrics (BLEU) we reached the highest score for this subtask with a nearly 2 BLEU point margin over the next strongest system. Based on human evaluation we ranked first among constrained systems. We believe this is mostly caused by our data filtering/weighting regime.
Tasks
Published	2018-09-01
URL	http://arxiv.org/abs/1809.00196v1
PDF	http://arxiv.org/pdf/1809.00196v1.pdf
PWC	https://paperswithcode.com/paper/microsofts-submission-to-the-wmt2018-news
Repo
Framework

Identifying emergency stages in Facebook posts of police departments with convolutional and recurrent neural networks and support vector machines


Title	Identifying emergency stages in Facebook posts of police departments with convolutional and recurrent neural networks and support vector machines
Authors	Nicolai Pogrebnyakov, Edgar Maldonado
Abstract	Classification of social media posts in emergency response is an important practical problem: accurate classification can help automate processing of such messages and help other responders and the public react to emergencies in a timely fashion. This research focused on classifying Facebook messages of US police departments. Randomly selected 5,000 messages were used to train classifiers that distinguished between four categories of messages: emergency preparedness, response and recovery, as well as general engagement messages. Features were represented with bag-of-words and word2vec, and models were constructed using support vector machines (SVMs) and convolutional (CNNs) and recurrent neural networks (RNNs). The best performing classifier was an RNN with a custom-trained word2vec model to represent features, which achieved the F1 measure of 0.839.
Tasks
Published	2018-01-02
URL	http://arxiv.org/abs/1801.00801v2
PDF	http://arxiv.org/pdf/1801.00801v2.pdf
PWC	https://paperswithcode.com/paper/identifying-emergency-stages-in-facebook
Repo
Framework

Adaptive Low-Nonnegative-Rank Approximation for State Aggregation of Markov Chains


Title	Adaptive Low-Nonnegative-Rank Approximation for State Aggregation of Markov Chains
Authors	Yaqi Duan, Mengdi Wang, Zaiwen Wen, Yaxiang Yuan
Abstract	This paper develops a low-nonnegative-rank approximation method to identify the state aggregation structure of a finite-state Markov chain under an assumption that the state space can be mapped into a handful of meta-states. The number of meta-states is characterized by the nonnegative rank of the Markov transition matrix. Motivated by the success of the nuclear norm relaxation in low rank minimization problems, we propose an atomic regularizer as a convex surrogate for the nonnegative rank and formulate a convex optimization problem. Because the atomic regularizer itself is not computationally tractable, we instead solve a sequence of problems involving a nonnegative factorization of the Markov transition matrices by using the proximal alternating linearized minimization method. Two methods for adjusting the rank of factorization are developed so that local minima are escaped. One is to append an additional column to the factorized matrices, which can be interpreted as an approximation of a negative subgradient step. The other is to reduce redundant dimensions by means of linear combinations. Overall, the proposed algorithm very likely converges to the global solution. The efficiency and statistical properties of our approach are illustrated on synthetic data. We also apply our state aggregation algorithm on a Manhattan transportation data set and make extensive comparisons with an existing method.
Tasks
Published	2018-10-14
URL	http://arxiv.org/abs/1810.06032v1
PDF	http://arxiv.org/pdf/1810.06032v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-low-nonnegative-rank-approximation
Repo
Framework

AI-based Two-Stage Intrusion Detection for Software Defined IoT Networks


Title	AI-based Two-Stage Intrusion Detection for Software Defined IoT Networks
Authors	Jiaqi Li, Zhifeng Zhao, Rongpeng Li, Honggang Zhang
Abstract	Software Defined Internet of Things (SD-IoT) Networks profits from centralized management and interactive resource sharing which enhances the efficiency and scalability of IoT applications. But with the rapid growth in services and applications, it is vulnerable to possible attacks and faces severe security challenges. Intrusion detection has been widely used to ensure network security, but classical detection means are usually signature-based or explicit-behavior-based and fail to detect unknown attacks intelligently, which are hard to satisfy the requirements of SD-IoT Networks. In this paper, we propose an AI-based two-stage intrusion detection empowered by software defined technology. It flexibly captures network flows with a globle view and detects attacks intelligently through applying AI algorithms. We firstly leverage Bat algorithm with swarm division and Differential Mutation to select typical features. Then, we exploit Random forest through adaptively altering the weights of samples using weighted voting mechanism to classify flows. Evaluation results prove that the modified intelligent algorithms select more important features and achieve superior performance in flow classification. It is also verified that intelligent intrusion detection shows better accuracy with lower overhead comparied with existing solutions.
Tasks	Intrusion Detection
Published	2018-06-07
URL	http://arxiv.org/abs/1806.02566v1
PDF	http://arxiv.org/pdf/1806.02566v1.pdf
PWC	https://paperswithcode.com/paper/ai-based-two-stage-intrusion-detection-for
Repo
Framework

Isometric Transformation Invariant Graph-based Deep Neural Network


Title	Isometric Transformation Invariant Graph-based Deep Neural Network
Authors	Renata Khasanova, Pascal Frossard
Abstract	Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for image and video classification tasks. However, they have achieved only limited success in the classification of images that undergo geometric transformations. In this work we present a novel Transformation Invariant Graph-based Network (TIGraNet), which learns graph-based features that are inherently invariant to isometric transformations such as rotation and translation of input images. In particular, images are represented as signals on graphs, which permits to replace classical convolution and pooling layers in deep networks with graph spectral convolution and dynamic graph pooling layers that together contribute to invariance to isometric transformation. Our experiments show high performance on rotated and translated images from the test set compared to classical architectures that are very sensitive to transformations in the data. The inherent invariance properties of our framework provide key advantages, such as increased resiliency to data variability and sustained performance with limited training sets. Our code is available online.
Tasks	Video Classification
Published	2018-08-21
URL	http://arxiv.org/abs/1808.07366v1
PDF	http://arxiv.org/pdf/1808.07366v1.pdf
PWC	https://paperswithcode.com/paper/isometric-transformation-invariant-graph
Repo
Framework

A Non-structural Representation Scheme for Articulated Shapes


Title	A Non-structural Representation Scheme for Articulated Shapes
Authors	Asli Genctav, Sibel Tari
Abstract	For representing articulated shapes, as an alternative to the structured models based on graphs representing part hierarchy, we propose a pixel-based distinctness measure. Its spatial distribution yields a partitioning of the shape into a set of regions each of which is represented via size normalized probability distribution of the distinctness. Without imposing any structural relation among parts, pairwise shape similarity is formulated as the cost of an optimal assignment between respective regions. The matching is performed via Hungarian algorithm permitting some unmatched regions. The proposed similarity measure is employed in the context of clustering a set of shapes. The clustering results obtained on three articulated shape datasets show that our method performs comparable to state of the art methods utilizing component graphs or trees even though we are not explicitly modeling component relations.
Tasks
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11411v1
PDF	http://arxiv.org/pdf/1807.11411v1.pdf
PWC	https://paperswithcode.com/paper/a-non-structural-representation-scheme-for
Repo
Framework

Analyze Unstructured Data Patterns for Conceptual Representation


Title	Analyze Unstructured Data Patterns for Conceptual Representation
Authors	Aboubakr Aqle, Dena Al-Thani, Ali Jaoua
Abstract	Online news media provides aggregated news and stories from different sources all over the world and up-to-date news coverage. The main goal of this study is to have a solution that considered as a homogeneous source for the news and to represent the news in a new conceptual framework. Furthermore, the user can easily find different updated news in a fast way through the designed interface. The Mobile App implementation is based on modeling the multi-level conceptual analysis discipline. Discovering main concepts of any domain is captured from the hidden unstructured data that are analyzed by the proposed solution. Concepts are discovered through analyzing data patterns to be structured into a tree-based interface for easy navigation for the end user, through the discovered news concepts. Our final experiment results showing that analyzing the news before displaying to the end-user and restructuring the final output in a conceptual multilevel structure, that producing new display frame for the end user to find the related information to his interest.
Tasks
Published	2018-08-29
URL	http://arxiv.org/abs/1808.10259v1
PDF	http://arxiv.org/pdf/1808.10259v1.pdf
PWC	https://paperswithcode.com/paper/analyze-unstructured-data-patterns-for
Repo
Framework

Learning Grid Cells as Vector Representation of Self-Position Coupled with Matrix Representation of Self-Motion


Title	Learning Grid Cells as Vector Representation of Self-Position Coupled with Matrix Representation of Self-Motion
Authors	Ruiqi Gao, Jianwen Xie, Song-Chun Zhu, Ying Nian Wu
Abstract	This paper proposes a representational model for grid cells. In this model, the 2D self-position of the agent is represented by a high-dimensional vector, and the 2D self-motion or displacement of the agent is represented by a matrix that transforms the vector. Each component of the vector is a unit or a cell. The model consists of the following three sub-models. (1) Vector-matrix multiplication. The movement from the current position to the next position is modeled by matrix-vector multiplication, i.e., the vector of the next position is obtained by multiplying the matrix of the motion to the vector of the current position. (2) Magnified local isometry. The angle between two nearby vectors equals the Euclidean distance between the two corresponding positions multiplied by a magnifying factor. (3) Global adjacency kernel. The inner product between two vectors measures the adjacency between the two corresponding positions, which is defined by a kernel function of the Euclidean distance between the two positions. Our representational model has explicit algebra and geometry. It can learn hexagon patterns of grid cells, and it is capable of error correction, path integral and path planning.
Tasks
Published	2018-10-12
URL	https://arxiv.org/abs/1810.05597v3
PDF	https://arxiv.org/pdf/1810.05597v3.pdf
PWC	https://paperswithcode.com/paper/learning-grid-cells-as-vector-representation
Repo
Framework

Model-based clustering for identifying disease-associated SNPs in case-control genome-wide association studies


Title	Model-based clustering for identifying disease-associated SNPs in case-control genome-wide association studies
Authors	Yan Xu, Li Xing, Jessica Su, Xuekui Zhang, Weiliang Qiu
Abstract	Genome-wide association studies (GWASs) aim to detect genetic risk factors for complex human diseases by identifying disease-associated single-nucleotide polymorphisms (SNPs). The traditional SNP-wise approach along with multiple testing adjustment is over-conservative and lack of power in many GWASs. In this article, we proposed a model-based clustering method that transforms the challenging high-dimension-small-sample-size problem to low-dimension-large-sample-size problem and borrows information across SNPs by grouping SNPs into three clusters. We pre-specify the patterns of clusters by minor allele frequencies of SNPs between cases and controls, and enforce the patterns with prior distributions. In the simulation studies our proposed novel model outperform traditional SNP-wise approach by showing better controls of false discovery rate (FDR) and higher sensitivity. We re-analyzed two real studies to identifying SNPs associated with severe bortezomib-induced peripheral neuropathy (BiPN) in patients with multiple myeloma (MM). The original analysis in the literature failed to identify SNPs after FDR adjustment. Our proposed method not only detected the reported SNPs after FDR adjustment but also discovered a novel BiPN-associated SNP rs4351714 that has been reported to be related to MM in another study.
Tasks
Published	2018-06-21
URL	http://arxiv.org/abs/1806.08456v2
PDF	http://arxiv.org/pdf/1806.08456v2.pdf
PWC	https://paperswithcode.com/paper/model-based-clustering-for-identifying
Repo
Framework

Vulcan: A Monte Carlo Algorithm for Large Chance Constrained MDPs with Risk Bounding Functions


Title	Vulcan: A Monte Carlo Algorithm for Large Chance Constrained MDPs with Risk Bounding Functions
Authors	Benjamin J Ayton, Brian C Williams
Abstract	Chance Constrained Markov Decision Processes maximize reward subject to a bounded probability of failure, and have been frequently applied for planning with potentially dangerous outcomes or unknown environments. Solution algorithms have required strong heuristics or have been limited to relatively small problems with up to millions of states, because the optimal action to take from a given state depends on the probability of failure in the rest of the policy, leading to a coupled problem that is difficult to solve. In this paper we examine a generalization of a CCMDP that trades off probability of failure against reward through a functional relationship. We derive a constraint that can be applied to each state history in a policy individually, and which guarantees that the chance constraint will be satisfied. The approach decouples states in the CCMDP, so that large problems can be solved efficiently. We then introduce Vulcan, which uses our constraint in order to apply Monte Carlo Tree Search to CCMDPs. Vulcan can be applied to problems where it is unfeasible to generate the entire state space, and policies must be returned in an anytime manner. We show that Vulcan and its variants run tens to hundreds of times faster than linear programming methods, and over ten times faster than heuristic based methods, all without the need for a heuristic, and returning solutions with a mean suboptimality on the order of a few percent. Finally, we use Vulcan to solve for a chance constrained policy in a CCMDP with over $10^{13}$ states in 3 minutes.
Tasks
Published	2018-09-04
URL	http://arxiv.org/abs/1809.01220v1
PDF	http://arxiv.org/pdf/1809.01220v1.pdf
PWC	https://paperswithcode.com/paper/vulcan-a-monte-carlo-algorithm-for-large
Repo
Framework

The University of Cambridge’s Machine Translation Systems for WMT18


Title	The University of Cambridge’s Machine Translation Systems for WMT18
Authors	Felix Stahlberg, Adria de Gispert, Bill Byrne
Abstract	The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation. We compare recurrent, convolutional, and self-attention-based neural models on German-English, English-German, and Chinese-English. Our final system combines all neural models together with a phrase-based SMT system in an MBR-based scheme. We report small but consistent gains on top of strong Transformer ensembles.
Tasks	Machine Translation
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09465v1
PDF	http://arxiv.org/pdf/1808.09465v1.pdf
PWC	https://paperswithcode.com/paper/the-university-of-cambridges-machine
Repo
Framework

Image-based Natural Language Understanding Using 2D Convolutional Neural Networks


Title	Image-based Natural Language Understanding Using 2D Convolutional Neural Networks
Authors	Erinc Merdivan, Anastasios Vafeiadis, Dimitrios Kalatzis, Sten Hanke, Johannes Kropf, Konstantinos Votis, Dimitrios Giakoumis, Dimitrios Tzovaras, Liming Chen, Raouf Hamzaoui, Matthieu Geist
Abstract	We propose a new approach to natural language understanding in which we consider the input text as an image and apply 2D Convolutional Neural Networks to learn the local and global semantics of the sentences from the variations ofthe visual patterns of words. Our approach demonstrates that it is possible to get semantically meaningful features from images with text without using optical character recognition and sequential processing pipelines, techniques that traditional Natural Language Understanding algorithms require. To validate our approach, we present results for two applications: text classification and dialog modeling. Using a 2D Convolutional Neural Network, we were able to outperform the state-of-art accuracy results of non-Latin alphabet-based text classification and achieved promising results for eight text classification datasets. Furthermore, our approach outperformed the memory networks when using out of vocabulary entities fromtask 4 of the bAbI dialog dataset.
Tasks	Optical Character Recognition, Text Classification
Published	2018-10-24
URL	http://arxiv.org/abs/1810.10401v2
PDF	http://arxiv.org/pdf/1810.10401v2.pdf
PWC	https://paperswithcode.com/paper/image-based-natural-language-understanding
Repo
Framework

Machine Learning: Basic Principles


Title	Machine Learning: Basic Principles
Authors	Alexander Jung
Abstract	This tutorial is based on the lecture notes for, and the plentiful student feedback received from, the courses “Machine Learning: Basic Principles” and “Artificial Intelligence”, which I have co-taught since 2015 at Aalto University. The aim is to provide an accessible introduction to some of the main concepts and methods within machine learning. Many of the current systems which are considered as (artificially) intelligent are based on combinations of few basic machine learning methods. After formalizing the main building blocks of a machine learning problem, some popular algorithmic design patterns for machine learning methods are discussed in some detail.
Tasks
Published	2018-05-14
URL	http://arxiv.org/abs/1805.05052v9
PDF	http://arxiv.org/pdf/1805.05052v9.pdf
PWC	https://paperswithcode.com/paper/machine-learning-basic-principles
Repo
Framework