检索结果-内蒙古大学图书馆

Sequence Modeling for intelligent Typing Assistant with Bangla and English Keyboard

学校读者我要写书评

暂无评论

Sequence Modeling for Intelligent Typing Assistant with Bang...

International Conference on Innovation in Engineering and Technology (ICIET)

作者： Shuvendu Roy Sk. Imran Hossain M. A. H. Akhand N. Siddique dept. of Computer Science and Engineering Khulna University of Engineering & Technology Khulna Bangladesh School of Computing Engineering and Intelligent Systems Ulster University United Kingdom

ISBN: (纸本)9781538652305;9781538652299

Typing Assistant is a helping tool that autocompletes writing, both by completing current words and suggesting relevant word sequences. Smart typing assistant is the one that can suggest more than just the current word. Based on the context, it is able to suggest the next few words that are relevant. In this work, we propose such a model using the recent advancement of the recurrent neural network. It is a context-aware model that can predict the next few words conditioning on the context user is writing. This is a general purpose solution to typing assistant system. Our work stands out from other research in two cases. First, rather than using only a temperature variable to introduce randomness in the generation and choosing only one character, we used beam search to generate multiple words suggestion. Second, we used encoder-decoder architecture to generate more than the one-word suggestion. Often more than one word of this suggestion is relevant enough to choose and that makes the typing more efficient. We tried it for both Bangla and English. In both cases, it gave impressive suggestions during typing.

关键词： Recurrent neural networks Task analysis Decoding Predictive models Training Computational modeling

Convexification of Neural Graph

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Xiao, Han State Key Lab. of Intelligent Technology and Systems National Lab. for Information Science and Technology Dept. of Computer Science and Technology Tsinghua University Beijing100084 China

Traditionally, most complex intelligence architectures are extremely non-convex, which could not be well performed by convex optimization. However, this paper decomposes complex structures into three types of nodes: operators, algorithms and functions. Iteratively, propagating from node to node along edge, we prove that "regarding the tree-structured neural graph, it is nearly convex in each variable, when the other variables are fixed." In fact, the non-convex properties stem from circles and functions, which could be transformed to be convex with our proposed scale mechanism. Experimentally, we justify our theoretical analysis by two practical applications. Copyright © 2018, The Authors. All rights reserved.

关键词： Trees (mathematics)

Relation mention extraction from noisy data with hierarchical reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Feng, Jun Huang, Minlie Zhang, Yijie Yang, Yang Zhu, Xiaoyan State Key Lab. of Intelligent Technology and Systems National Lab. for Information Science and Technology Dept. of Computer Science and Technology Tsinghua University Beijing100084 China College of Computer Science and Technology Zhejiang University

In this paper we address a task of relation mention extraction from noisy data: extracting representative phrases for a particular relation from noisy sentences that are collected via distant supervision. Despite its significance and value in many downstream applications, this task is less studied on noisy data. The major challenges exists in 1) the lack of annotation on mention phrases, and more severely, 2) handling noisy sentences which do not express a relation at all. To address the two challenges, we formulate the task as a semi-Markov decision process and propose a novel hierarchical reinforcement learning model. Our model consists of a top-level sentence selector to remove noisy sentences, a low-level mention extractor to extract relation mentions, and a reward estimator to provide signals to guide data denoising and mention extraction without explicit annotations. Experimental results show that our model is effective to extract relation mentions from noisy data. Copyright © 2018, The Authors. All rights reserved.

关键词： Extraction

A de-centralized framework for data sharing, ontology matching and distributed analytics 1

学校读者我要写书评

暂无评论

A de-centralized framework for data sharing, ontology matchi...

1st International Workshop on Semantic Web Technologies for Health Data Management, SWH 2018

作者： Pezoulas, Vasileios C. Kourou, Konstantina D. Exarchos, Themis P. An-dronikou, Vassiliki Varvarigou, Theodora Tzioufas, Athanasios G. De Vita, Salvatore Fotiadis, Dimitrios I. Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering University of Ioannina IoanninaGR 45110 Greece Dept. of Informatics Ionian University CorfuGR 49100 Greece Division of Communication Electronic and Information Engineering School of Electrical and Computer Engineering National Technical University of Athens AthensGR 15780 Greece Dept. of Pathophysiology Faculty of Medicine National and Kapodistrian University of Athens AthensGR 15772 Greece Clinic of Rheumatology Dept. of Medical and Biological Sciences Udine University UdineIT 33100 Italy

In this paper we present the fundamental concept, as well as, the objectives and the architecture of HarmonicSS EU project. The proposed architecture envisages to address (i) the lack of patient stratification in large patient cohorts, (ii) the dataset heterogeneity across these cohorts, and (iii) the incomplete understanding of disease pathogenesis. In order to do so, ontology matching mechanisms are recruited for harmonizing the clinical data, distributed data analytics services have been designed for the de-centralized analysis of patient data, and different health policies can be assessed, all of them with respect to the data protection guidelines posed by the upcoming General Data Protection Regulation (GDPR). The HarmonicSS architecture has been employed towards the development of a data sharing, harmonization and distributed analytics framework for the recruitment and analysis of heterogeneous regional, national and international longitudinal cohorts of patients with primary Sjögren’s syndrome (pSS). The outcomes can be used by researchers, clinicians, patients, and health policy makers. © 2018 CEUR-WS. All rights reserved.

关键词： Large dataset

Exploring the effect of image enhancement techniques on COVID‐19 detection using chest X‐rays images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Rahman, Tawsifur Khandakar, Amith Qiblawey, Yazan Tahir, Anas Kiranyaz, Serkan Kashem, Saad Bin Abul Islam, Mohammad Tariqul Maadeed, Somaya Al Zughaier, Susu M. Khan, Muhammad Salman Chowdhury, Muhammad E.H. Department of Biomedical Physics & Technology University of Dhaka Dhaka 1000 Bangladesh Department of Electrical Engineering Qatar University Doha2713 Qatar Faculty of Robotics and Advanced Computing Qatar Armed Forces‐Academic Bridge Program Qatar Foundation Doha24404 Qatar Dept. of Electrical Electronics and Systems Engineering Universiti Kebangsaan Malaysia BangiSelangor43600 Malaysia Department of Computer Science and Engineering Qatar University Doha2713 Qatar Department of Basic Medical Sciences College of Medicine Biomedical and Pharmaceutical Research Unit QU Health Qatar University Doha2713 Qatar University of Engineering and Technology Peshawar Pakistan

The use of computer-aided diagnosis in the reliable and fast detection of corona virus disease (COVID-19) has become a necessity to prevent the spread of the virus during the pandemic to ease the burden on the medical infrastructure. Chest X-ray (CXR) imaging has several advantages over other imaging techniques as it is cheap, easily accessible, fast and portable. CXR images are sometimes of poor quality and so image enhancement techniques can help the machine learning models to extract valuable discriminating features from the image. Numerous works have been reported on COVID-19 detection from smaller set of original X-ray images. However, the effect of image enhancement in COVID-19 detection was not reported in the literature. This paper explores the effect of various popular image enhancement techniques and states the © 2020, CC BY.

关键词： Image enhancement

Modified Grey Wolf Optimization to Solve Traveling Salesman Problem

学校读者我要写书评

暂无评论

Modified Grey Wolf Optimization to Solve Traveling Salesman ...

International Conference on Innovation in Engineering and Technology (ICIET)

作者： Dibbendu Singha Sopto Safial Islam Ayon M. A. H. Akhand N. Siddique Dept. of Computer Science and Engineering Khulna University of Engineering & Technology Khulna Bangladesh School of Computing Engineering and Intelligent Systems Ulster University Northern Ireland United Kingdom

ISBN: (纸本)9781538652305;9781538652299

Traveling Salesman Problem (TSP) is arguably the most familiar combinatorial optimization problem. TSP is also a very popular benchmark problem for performance verification of new optimization algorithms even though the algorithms are developed for different problems such as numerical optimization. This paper proposes a new method to solve TSP based on a recently developed optimization method inspired by the hunting and social behavior of the grey wolf pack. Standard Grey Wolf Optimization (GWO) is developed for numerical optimization; GWO is modified and adapted in this study considering Swap Operator (SO) and Swap Sequence (SS) implication for TSP. SS is an arrangement of several SOs in which each SO holds two particular positions in a TSP solution that can be swapped to make a new solution. In the proposed modified GWO, each grey wolf is considered as a TSP solution and SS is considered to update the solution. In every iteration, a new tour is formed by swapping positions indicated by SOs of the SS to the previous solution. The proposed technique is tested on several instances of the benchmark TSP and the final results are compared with the other well-known methods. Experimental results show that the proposed method is a decent technique to resolve TSP.

关键词： Optimization Sociology Statistics Urban areas Benchmark testing Standards Genetic algorithms

FCLAB: An EEGLAB module for performing functional connectivity analysis on single-subject EEG data

学校读者我要写书评

暂无评论

FCLAB: An EEGLAB module for performing functional connectivi...

2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018

作者： Pezoulas, Vasileios C. Athanasiou, Alkinoos Nolte, Guido Zervakis, Michalis Fratini, Antonio Fotiadis, Dimitrios I. Klados, Manousos A. Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering University of Ioannina Ioannina45112 Greece Lab of Medical Physics Faculty of Medicine School of Health Sciences Aristotle University of Thessaloniki Thessaloniki54124 Greece Dept. of Neurophysiology and Pathophysiology University Medical Center Hamburg-Eppendorf Hamburg Germany School of Electrical and Computer Engineering Technical University of Crete Chania73100 Greece Dept. of Biomedical Engineering School of Life and Health Sciences Aston University Aston United Kingdom

ISBN: (纸本)9781538624050

Functional connectivity (FC) analysis constitutes a fundamental neuroscientific approach that has been extensively used for the investigation of brain's connectivity and activation patterns. To that end, several software tools have been developed. This paper presents FCLAB, the only EEGLAB-based plugin, which is able to work with EEG signals in order to estimate and visualize brain functional connectivity networks based on a variety of similarity measures as well as run a complete graph analysis procedure followed by a detailed visualization of the ensuing local and global measures distribution. FCLAB entails optimization procedures for the implementation of the connectivity structures and is the result of long-term research in EEG functional connectivity. The computed functional connectivity measures have been carefully selected to reflect the state-of-art in the field. Future work focuses on extending the platform for multi-subject analysis in order to enable the implementation of statistical analysis tools. © 2018 IEEE.

关键词： Neurophysiology

Reinforcement learning for relation classification from noisy data

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Feng, Jun Huang, Minlie Zhao, Li Yang, Yang Zhu, Xiaoyan State Key Lab. of Intelligent Technology and Systems National Lab. for Information Science and Technology Dept. of Computer Science and Technology Tsinghua University Beijing100084 China Microsoft Research Asia College of Computer Science and Technology Zhejiang University

Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair. Such methods, performing classification at the bag level, cannot identify the mapping between a relation and a sentence, and largely suffers from the noisy labeling problem. In this paper, we propose a novel model for relation classification at the sentence level from noisy data. The model has two modules: an instance selector and a relation classifier. The instance selector chooses high-quality sentences with reinforcement learning and feeds the selected sentences into the relation classifier, and the relation classifier makes sentencelevel prediction and provides rewards to the instance selector. The two modules are trained jointly to optimize the instance selection and relation classification processes. Experiment results show that our model can deal with the noise of data effectively and obtains better performance for relation classification at the sentence level. Copyright © 2018, The Authors. All rights reserved.

关键词： Reinforcement learning

Boosting black box variational inference

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Locatello, Francesco Dresdner, Gideon Khanna, Rajiv Valera, Isabel Rätsch, Gunnar Max-Planck Institute for Intelligent Systems Germany Dept. for Computer Science ETH Zurich Universitätsstrasse 6 Zurich8092 Switzerland University of Texas Austin United States

Approximating a probability density in a tractable manner is a central task in Bayesian statistics. Variational Inference (VI) is a popular technique that achieves tractability by choosing a relatively simple variational approximation. Borrowing ideas from the classic boosting framework, recent approaches attempt to boost VI by replacing the selection of a single density with an iteratively constructed mixture of densities. In order to guarantee convergence, previous works impose stringent assumptions that require significant effort for practitioners. Specifically, they require a custom implementation of the greedy step (called the LMO) for every probabilistic model with respect to an unnatural variational family of truncated distributions. Our work fixes these issues with novel theoretical and algorithmic insights. On the theoretical side, we show that boosting VI satisfies a relaxed smoothness assumption which is sufficient for the convergence of the functional Frank-Wolfe (FW) algorithm. Furthermore, we rephrase the LMO problem and propose to maximize the Residual ELBO (RELBO) which replaces the standard ELBO optimization in VI. These theoretical enhancements allow for black box implementation of the boosting subroutine. Finally, we present a stopping criterion drawn from the duality gap in the classic FW analyses and exhaustive experiments to illustrate the usefulness of our theoretical and algorithmic contributions. Copyright © 2018, The Authors. All rights reserved.

关键词： Iterative methods