检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Min, Seonwoo Park, Seunghyun Kim, Siwon Choi, Hyun-Soo Lee, Byunghan Yoon, Sungroh Department of Electrical and Computer engineering Seoul National University Seoul08826 Korea Republic of LG AI Research Seoul07796 Korea Republic of Clova AI Research NAVER Corp. Seongnam13561 Korea Republic of Department of Computer Science and Engineering Kangwon National University Chuncheon24341 Korea Republic of Department of Electronic and IT Media Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of Interdisciplinary Program in Artificial Intelligence ASRI INMC Institute of Engineering Research Seoul National University Seoul08826 Korea Republic of

Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling. In these studies, models were pre-trained with a substantial amount of unlabeled data, and the representations were transferred to various downstream tasks. Most pre-training methods solely rely on language modeling and often exhibit limited performance. In this paper, we introduce a novel pre-training scheme called PLUS, which stands for Protein sequence representations Learned Using Structural information. PLUS consists of masked language modeling and a complementary protein-specific pre-training task, namely same-family prediction. PLUS can be used to pre-train various model architectures. In this work, we use PLUS to pre-train a bidirectional recurrent neural network and refer to the resulting model as PLUS-RNN. Our experiment results demonstrate that PLUS-RNN outperforms other models of similar size solely pre-trained with the language modeling in six out of seven widely used protein biology tasks. Furthermore, we present the results from our qualitative interpretation analyses to illustrate the strengths of PLUS-RNN. PLUS provides a novel way to exploit evolutionary relationships among unlabeled proteins and is broadly applicable across a variety of protein biology tasks. We expect that the gap between the numbers of unlabeled and labeled proteins will continue to grow exponentially, and the proposed pre-training method will play a larger role. All the data and codes used in this study are available at https://***/mswzeus/PLUS. © 2019, CC BY-NC-ND.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Adaptive activation network and functional regularization for efficient and flexible deep multi-task learning

arXiv

引用

arXiv 2019年

作者： Liu, Yingru Yang, Xuewen Xie, Dongliang Wang, Xin Shen, Li Huang, Haozhi Balasubramanian, Niranjan Department of Electrical and Computer Engineering Stony Brook University New York United States Institute of Network Technology Beijing University of Posts and Telecomunications Beijing China Department of Computer Science Stony Brook University New York United States Tencent AI Lab Shenzhen China

Multi-task learning (MTL) is a common paradigm that seeks to improve the generalization performance of task learning by training related tasks simultaneously. However, it is still a challenging problem to search the flexible and accurate architecture that can be shared among multiple tasks. In this paper, we propose a novel deep learning model called Task Adaptive Activation Network (TAAN) that can automatically learn the optimal network architecture for MTL. The main principle of TAAN is to derive flexible activation functions for different tasks from the data with other parameters of the network fully shared. We further propose two functional regularization methods that improve the MTL performance of TAAN. The improved performance of both TAAN and the regularization methods is demonstrated by comprehensive experiments. Copyright © 2019, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Joint Channel Estimation and Signal Recovery for RIS-Empowered Multi-User Communications

arXiv

引用

arXiv 2021年

作者： Wei, Li Huang, Chongwen Guo, Qinghua Yang, Zhaohui Zhang, Zhaoyang Alexandropoulos, George C. Debbah, Mérouane Yuen, Chau Pillar Singapore University of Technology and Design Singapore487372 Singapore College of Information Science and Electronic Engineering Zhejiang University Hangzhou310007 China Hangzhou310007 China International Joint Innovation Center Zhejiang University Haining314400 China Zhejiang-Singapore Innovation and AI Joint Research Lab Hangzhou310027 China Zhejiang Laboratory Hangzhou31121 China School of Electrical Computer and Telecommunications Engineering University of Wollongong WollongongNSW2522 Australia Department of Informatics and Telecommunications National and Kapodistrian University of Athens Panepistimiopolis Ilissia Athens15784 Greece Technology Innovation Institute Masdar City Abu Dhabi9639 United Arab Emirates CentraleSupelec University Paris-Saclay Gif-sur-Yvette91192 France

Reconfigurable intelligent surfaces (RISs) have been recently considered as a promising candidate for energy-efficient solutions in future wireless networks. Their dynamic and low-power configuration enables coverage extension, massive connectivity, and low-latency communications. Due to a large number of unknown variables referring to the RIS unit elements and the transmitted signals, channel estimation and signal recovery in RIS-based systems are the ones of the most critical technical challenges. To address this problem, we focus on the RIS-assisted wireless communication system and present two joint channel estimation and signal recovery schemes based on message passing algorithms in this paper. Specifically, the proposed bidirectional scheme applies the Taylor series expansion and Gaussian approximation to simplify the sum-product procedure in the formulated problem. In addition, the inner iteration that adopts two variants of approximate message passing algorithms is incorporated to ensure robustness and convergence. Two ambiguities removal methods are also discussed in this paper. Our simulation results show that the proposed schemes show the superiority over the state-of-art benchmark method. We also provide insights on the impact of different RIS parameter settings on the proposed schemes. Copyright © 2021, The Authors. All rights reserved.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

NTU NLP Lab System at SemEval-2018 Task 10: Verifying Semantic Differences by Integrating Distributional Information and Expert Knowledge

NTU NLP Lab System at SemEval-2018 Task 10: Verifying Semant...

引用

12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the

作者： Shiue, Yow-Ting Huang, Hen-Hsen Chen, Hsin-Hsi Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan MOST Joint Research Center for AI Technology All Vista Healthcare Taiwan

ISBN: (纸本)9781948087209

This paper presents the NTU NLP Lab system for the SemEval-2018 Capturing Discriminative Attributes task. Word embeddings, pointwise mutual information (PMI), ConceptNet edges and shortest path lengths are utilized as input features to build binary classifiers to tell whether an attribute is discriminative for a pair of concepts. Our neural network model reaches about 73% F1 score on the test set and ranks the 3rd in the task. Though the attributes to deal with in this task are all visual, our models are not provided with any image data. The results indicate that visual information can be derived from textual data. © 2018 Association for Computational Linguistics

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

MedShapeNet - A Large-Scale Dataset of 3D Medical Shapes for computer Vision

arXiv

引用

arXiv 2023年

作者： Li, Jianning Zhou, Zongwei Yang, Jiancheng Pepe, Antonio Gsaxner, Christina Luijten, Gijs Qu, Chongyu Zhang, Tiezheng Chen, Xiaoxi Li, Wenxuan Wodzinski, Marek Friedrich, Paul Xie, Kangxian Jin, Yuan Ambigapathy, Narmada Nasca, Enrico Solak, Naida Melito, Gian Marco Vu, Viet Duc Memon, Afaque R. Schlachta, Christopher De Ribaupierre, Sandrine Patel, Rajnikant Eagleson, Roy Chen, Xiaojun Mächler, Heinrich Kirschke, Jan Stefan de la Rosa, Ezequiel Christ, Patrick Ferdinand Li, Hongwei Bran Ellis, David G. aizenberg, Michele R. Gatidis, Sergios Küstner, Thomas Shusharina, Nadya Heller, Nicholas Andrearczyk, Vincent Depeursinge, Adrien Hatt, Mathieu Sekuboyina, Anjany Löffler, Maximilian Liebl, Hans Dorent, Reuben Vercauteren, Tom Shapey, Jonathan Kujawa, Aaron Cornelissen, Stefan Langenhuizen, Patrick Ben-Hamadou, Achraf Rekik, Ahmed Pujades, Sergi Boyer, Edmond Bolelli, Federico Grana, Costantino Lumetti, Luca Salehi, Hamidreza Ma, Jun Zhang, Yao Gharleghi, Ramtin Beier, Susann Sowmya, Arcot Garza-Villarreal, Eduardo A. Balducci, Thania Angeles-Valdez, Diego Souza, Roberto Rittner, Leticia Frayne, Richard Ji, Yuanfeng Ferrari, Vincenzo Chatterjee, Soumick Dubost, Florian Schreiber, Stefanie Mattern, Hendrik Speck, Oliver Haehn, Daniel John, Christoph Nürnberger, Andreas Pedrosa, João Ferreira, Carlos Aresta, Guilherme Cunha, António Campilho, Aurélio Suter, Yannick Garcia, Jose Lalande, Alain Vandenbossche, Vicky Van Oevelen, Aline Duquesne, Kate Mekhzoum, Hamza Vandemeulebroucke, Jef Audenaert, Emmanuel Krebs, Claudia van Leeuwen, Timo Vereecke, Evie Heidemeyer, Hauke Röhrig, Rainer Hölzle, Frank Badeli, Vahid Krieger, Kathrin Gunzer, Matthias Chen, Jianxu van Meegdenburg, Timo Dada, Amin Balzer, Miriam Fragemann, Jana Jonske, Frederic Rempe, Moritz Malorodov, Stanislav Bahnsen, Fin H. Seibold, Constantin Jaus, Alexander Marinov, Zdravko Jaeger, Paul F. Stiefelhagen, Rainer Santos, Ana Sofia Lindo, Mariana Ferreira, André Alves, Victor Kamp, Michael Abourayya, Amr Nensa, Felix Hörst, Fabian Brehmer, Alexander Hein Girardetstraße 2 Essen45131 Germany Graz University of Technology Inffeldgasse 16c Graz8010 Austria Graz Austria The Department of Computer Science Johns Hopkins University Malone Hall 3400 N Charles St BaltimoreMD21218 United States Rte Cantonale Lausanne1015 Switzerland The Department of Measurement and Electronics AGH University of Science and Technology Krakow Poland Sierre Switzerland Department of Biomedical Engineering University of Basel Hegenheimermattweg Allschwil167C CH-4123 Switzerland The Boston College 140 Commonwealth Ave Chestnut HillMA02467 United States University Hospital B7-200 339 Windermere Road LondonN6A 5A5 Canada The Department of Radiology Renji Hospital School of Medicine Shanghai Jiao Tong University Shanghai200240 China The Research Center for Connected Healthcare Big Data ZhejiangLab Zhejiang Hangzhou311121 China The Faculty of Statistics Technical University Dortmund August-Schmidt-Straße 1 Dortmund44227 Germany The Institute of Mechanics Graz University of Technology Kopernikusgasse 24/IV Graz8010 Austria The Institute of Biomedical Manufacturing and Life Quality Engineering State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China The Department of Cardiac Surgery Medical University Graz Auenbruggerplatz 29 Graz8036 Austria The Department of Diagnostic and Interventional Radiology University Hospital Giessen Justus-Liebig-University Giessen Klinikstraße 33 Giessen35392 Germany The Department of Mechanical Engineering Mehran University of Engineering and Technology Jamshoro Sindh76062 Pakistan The Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China The Geschäftsführender Oberarzt Abteilung für Interventionelle und Diagnostische Neuroradiologie Universitätsklinikum der Technischen Universität München Ismaningerstr. 22 München81675 Germany icometrix Kolonel Be

Prior to the deep learning era, shape was commonly used to describe the objects. Nowadays, state-of-the-art (SOTA) algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models are used. This is seen from numerous shape-related publications in premier vision conferences as well as the growing popularity of ShapeNet (about 51,300 models) and Princeton ModelNet (127,915 models). For the medical domain, we present a large collection of anatomical shapes (e.g., bones, organs, vessels) and 3D models of surgical instrument, called MedShapeNet, created to facilitate the translation of data-driven vision algorithms to medical applications and to adapt SOTA vision algorithms to medical problems. As a unique feature, we directly model the majority of shapes on the imaging data of real patients. As of today, MedShapeNet includes 23 datasets with more than 100,000 shapes that are paired with annotations (ground truth). Our data is freely accessible via a web interface and a Python application programming interface (API) and can be used for discriminative, reconstructive, and variational benchmarks as well as various applications in virtual, augmented, or mixed reality, and 3D printing. Exemplary, we present use cases in the fields of classification of brain tumors, skull reconstructions, multi-class anatomy completion, education, and 3D printing. In future, we will extend the data and improve the interfaces. The project pages are: https://***/ and https://***/Jianningli/*** Codes 68T01 © 2023, CC BY.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Visual concept selection with textual knowledge for understanding activities of daily living and life moment retrieval 19

Visual concept selection with textual knowledge for understa...

引用

19th Working Notes of CLEF Conference and Labs of the Evaluation Forum, CLEF 2018

作者： Tang, Tsun-Hsien Fu, Min-Huan Huang, Hen-Hsen Chen, Kuan-Ta Chen, Hsin-Hsi Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Institute of Information Science Academia Sinica Taipei Taiwan MOST Joint Research Center for AI Technology All Vista Healthcare Taipei Taiwan

This paper presents our approach to the task of ImageCLEFlifelog 2018. Two subtasks, activities of daily living understanding (ADLT) and life moment retrieval (LMRT) are addressed. We attempt to reduce the user involvement during the retrieval stage by using natural language processing technologies. The two subtasks are conducted with dedicated pipelines, while similar methodology is shared. We first obtain visual concepts from the images with a wide range of computer vision tools and propose a concept selection method to prune the noisy concepts with word embeddings in which textual knowledge is inherent. For ADLT, the retrieved images of a given topic are sorted by time, and the frequency and duration are further calculated. For LMRT, the retrieval is based on the ranking of similarity between image concepts and user queries. In terms of the performance, our systems achieve 47.87% of percentage dissimilarity in ADLT and 39.5% of F1@10 in LMRT.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Dash net: A hybrid artificial and spiking neural network for high-speed object tracking

arXiv

引用

arXiv 2019年

作者： Yang, Zheyu Wu, Yujie Wang, Guanrui Yang, Yukuan Li, Guoqi Deng, Lei Zhu, Jun Shi, Luping Department of Precision Instruments Tsinghua University Beijing100084 China State Key Lab of Intelligence Technology and System Department of Computer Science and Technology Institute for AI THBI Lab Tsinghua University Beijing100084 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States

computer-science-oriented artificial neural networks (ANNs) have achieved tremendous success in a variety of scenarios via powerful feature extraction and high-precision data operations. It is well known, however, that ANNs usually suffer from expensive processing resources and costs. In contrast, neuroscience-oriented spiking neural networks (SNNs) are promising for energy-efficient information processing benefit from the event-driven spike activities, whereas, they are yet be evidenced to achieve impressive effectiveness on real complicated tasks. How to combine the advantage of these two model families is an open question of great interest. Two significant challenges need to be addressed: (1) lack of benchmark datasets including both ANN-oriented (frames) and SNN-oriented (spikes) signal resources;(2) the difficulty in jointly processing the synchronous activation from ANNs and event-driven spikes from SNNs. In this work, we proposed a hybrid paradigm, named as DashNet, to demonstrate the advantages of combining ANNs and SNNs in a single model. A simulator and benchmark dataset "NFS-DAVIS" is built, and a temporal complementary filter (TCF) and attention module are designed to address the two mentioned challenges, respectively. In this way, it is shown that DashNet achieves the record-breaking speed of 2083FPS on neuromorphic chips and the best tracking performance on NFS-DAVIS and PRED18 datasets. To the best of our knowledge, DashNet is the first framework that can integrate and process ANNs and SNNs in a hybrid paradigm, which provides a novel solution to achieve both effectiveness and efficiency for high-speed object tracking. Copyright © 2019, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Industry-Scale Orchestrated Federated Learning for Drug Discovery

arXiv

引用

arXiv 2022年

作者： Oldenhof, Martijn Ács, Gergely Pejó, Balázs Schuffenhauer, Ansgar Holway, Nicholas Sturm, Noé Dieckmann, Arne Fortmeier, Oliver Boniface, Eric Mayer, Clément Gohier, Arnaud Schmidtke, Peter Niwayama, Ritsuya Kopecky, Dieter Mervin, Lewis Rathi, Prakash Chandra Friedrich, Lukas Formanek, András Antal, Peter Rahaman, Jordon Zalewski, Adam Heyndrickx, Wouter Oluoch, Ezron Stößel, Manuel Vančo, Michal Endico, David Gelus, Fabien De Boisfossé, Thaïs Darbier, Adrien Nicollet, Ashley Blottière, Matthieu Telenczuk, Maria Nguyen, Van Tien Martinez, Thibaud Boillet, Camille Moutet, Kelvin Picosson, Alexandre Gasser, Aurélien Djafar, Inal Simon, Antoine Arany, Ádám Simm, Jaak Moreau, Yves Engkvist, Ola Ceulemans, Hugo Marini, Camille Galtier, Mathieu Ku Leuven ESAT-STADIUS Kasteelpark Arenberg 10 Heverlee3001 Belgium BME-HIT CrySyS Lab Budapest Hungary BME-MIT Budapest Hungary Novartis Institutes for BioMedical Research Novartis Campus BaselCH-4002 Switzerland Bayer Ag Leverkusen51373 Germany Substra Foundation Labelia Labs Nantes France Discngine 79 Avenue Ledru Rollin Paris75012 France Institut de Recherches Servier 125 chemin de ronde Croissy-sur-Seine78290 France Boehringer Ingelheim Rcv GmbH & Co Kg Vienna Austria Molecular Ai Discovery Sciences R&d AstraZeneca Cambridge United Kingdom R&d It AstraZeneca Cambridge United Kingdom Molecular Ai Discovery Sciences R&d AstraZeneca Gothenburg Sweden Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden Merck KGaA Global Research & Development Frankfurter Strasse 250 Darmstadt64293 Germany GmbH Staffelseestraße 2 Munich81477 Germany Pillar Biosciences Inc. 9 Strathmore Rd NatickMA01760 United States Janssen Pharmaceutica Nv Turnhoutseweg 30 Beerse2340 Belgium Kubermatic Hamburg Germany Owkin Paris France

To apply federated learning to drug discovery we developed a novel platform in the context of European Innovative Medicines Initiative (IMI) project MELLODDY (grant n°831472), which was comprised of 10 pharmaceutical companies, academic research labs, large industrial companies and startups. The MELLODDY platform was the first industry-scale platform to enable the creation of a global federated model for drug discovery without sharing the confidential data sets of the individual partners. The federated model was trained on the platform by aggregating the gradients of all contributing partners in a cryptographic, secure way following each training iteration. The platform was deployed on an Amazon Web Services (AWS) multi-account architecture running Kubernetes clusters in private subnets. Organisationally, the roles of the different partners were codified as different rights and permissions on the platform and administrated in a decentralized way. The MELLODDY platform generated new scientific discoveries which are described in a companion paper. Copyright © 2022, The Authors. All rights reserved.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels

arXiv

引用

arXiv 2019年

作者： Jiang, Yihan Kannan, Sreeram Kim, Hyeji Oh, Sewoong Asnani, Himanshu Viswanath, Pramod ECE Department University of Washington Seattle United States Samsung AI Center Cambridge Cambridge United Kingdom Allen School of Computer Science & Engineering University of Washington Seattle United States School of Technology and Computer Science Tata Institute of Fundamental Research Mumbai India ECE Department University of Illinois at Urbana Champaign IL United States

Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications. Asymptotically optimal channel codes have been developed by mathematicians for communicating under canonical models after over 60 years of research. On the other hand, in many non-canonical channel settings, optimal codes do not exist and the codes designed for canonical models are adapted via heuristics to these channels and are thus not guaranteed to be optimal. In this work, we make significant progress on this problem by designing a fully end-to-end jointly trained neural encoder and decoder, namely, Turbo Autoencoder (TurboAE), with the following contributions: (a) under moderate block lengths, TurboAE approaches state-of-the-art performance under canonical channels;(b) moreover, TurboAE outperforms the state-of-the-art codes under non-canonical settings in terms of reliability. TurboAE shows that the development of channel coding design can be automated via deep learning, with near-optimal performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Channel coding

来源：评论

学校读者我要写书评

暂无评论

Subgraph networks with application to structural feature space expansion

arXiv

引用

arXiv 2019年

作者： Xuan, Qi Wang, Jinhuan Zhao, Minghao Yuan, Junkun Fu, Chenbo Ruan, Zhongyuan Chen, Guanrong Institute of Cyberspace Security College of Information Engineering Zhejiang University of Technology Hangzhou China Fuxi AI Lab NetEase Inc. Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China Department of Electronic Engineering City University of Hong Kong Hong Kong

Real-world networks exhibit prominent hierarchical and modular structures, with various subgraphs as building blocks. Most existing studies simply consider distinct subgraphs as motifs and use only their numbers to characterize the underlying network. Although such statistics can be used to describe a network model, or even to design some network algorithms, the role of subgraphs in such applications can be further explored so as to improve the results. In this paper, the concept of subgraph network (SGN) is introduced and then applied to network models, with algorithms designed for constructing the 1st-order and 2nd-order SGNs, which can be easily extended to build higher-order ones. Furthermore, these SGNs are used to expand the structural feature space of the underlying network, beneficial for network classification. Numerical experiments demonstrate that the network classification model based on the structural features of the original network together with the 1st-order and 2nd-order SGNs always performs the best as compared to the models based only on one or two of such networks. In other words, the structural features of SGNs can complement that of the original network for better network classification, regardless of the feature extraction method used, such as the handcrafted, network embedding and kernel-based methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：