检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Thy Nguyen Emmett Redd A. Steven Younger Tayo Obafemi-Ajayi Computer Science Dept. Missouri State University Springfield MO Department of Physics Astronomy and Materials Science Missouri State University Springfield MO Engineering Program Missouri State University Springfield MO

There have been recent interest in meta-learning systems: i.e. networks that are trained to learn across multiple tasks. This paper focuses on optimization and generalization of a meta-learning system based on recurrent networks. The optimization investigates the influence of diverse structures and parameters on its performance. We demonstrate the generalization (robustness) of our meta-learning system to learn across multiple tasks including tasks unseen during the metatraining phase. We introduce a meta-cost function (Mean Squared Fair Error) that enhances the performance of the system by not penalizing it during transitions to learning a new task. Evaluation results are presented for Boolean and quadratic functions datasets. The best performance is obtained using a Long Short-Term Memory (LSTM) topology without a forget gate and with a clipped memory cell. The results demonstrate i) the impact of different LSTM architectures, parameters, and error functions on the meta-learning process;ii) that the mean squared fair error function does improve performance for best learning;and iii) the robustness of our meta-learning framework as it generalizes well when tested on tasks unseen during metatraining. Comparison between No-Forget-Gate LSTM and Gated Recurrent Unit also suggest that absence of a memory cell tends to degrade performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Syncgan: Synchronize the Latent Spaces of Cross-Modal Generative Adversarial Networks

Syncgan: Synchronize the Latent Spaces of Cross-Modal Genera...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wen-Cheng Chen Chien-Wen Chen Min-Chun Hu Dept. of Computer Science and Information Engineering National Cheng Kung University Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

Generative adversarial network (GAN) has achieved impressive success on cross-domain generation, but it faces difficulty in cross-modal generation due to the lack of a common distribution between heterogeneous data. Most existing methods of conditional based cross-modal GANs adopt the strategy of one-directional transfer and have achieved preliminary success on text-to-image transfer. Instead of learning the transfer between different modalities, we aim to learn a synchronous latent space representing the cross-modal common concept. A novel network component named synchronizer is proposed in this work to judge whether the paired data is synchronous/corresponding or not, which can constrain the latent space of generators in the GANs. Our GAN model, named as SyncGAN, can successfully generate synchronous data (e.g., a pair of image and sound) from identical random noise. For transforming data from one modality to another, we recover the latent code by inverting the mappings of a generator and use it to generate data of different modality. In addition, the proposed model can achieve semi-supervised learning, which makes our model more flexible for practical applications.

关键词： Synchronization Gallium nitride Generators Data models Training Generative adversarial networks Training data

来源：评论

学校读者我要写书评

暂无评论

Symbol Emergence in Cognitive Developmental Systems: A Survey

arXiv

引用

arXiv 2018年

作者： Taniguchi, Tadahiro Ugur, Emre Hoffmann, Matej Jamone, Lorenzo Nagai, Takayuki Rosman, Benjamin Matsuka, Toshihiko Iwahashi, Naoto Oztop, Erhan Piater, Justus Wörgötter, Florentin College of Information Science and Engineering Ritsumeikan University 1-1-1 Noji Higashi Shiga Kusatsu525-8577 Japan Dept. of Computer Engineering Bogazici University Istanbul Turkey Dept. Cybernetics Faculty of Electrical Engineering Czech Technical University Prague Czech Republic School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Faculty of Informatics and Engineering The University of Electro-communications Japan Mobile Intelligent Autonomous Systems The Council for Scientific and Industrial Research The School of Computer Science and Applied Mathematics The University of the Witwatersrand South Africa Department of Cognitive and Information Science Chiba University Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Japan Dept. of Computer Science Ozyegin University Istanbul Turkey The Dept. of Computer Science Universität Innsbruck Austria The Department for Computational Neuroscience The Bernstein Center of the University of Göttingen Inst. F. Physics Iii Germany

Humans use signs, e.g., sentences in a spoken language, for communication and thought. Hence, symbol systems like language are crucial for our communication with other agents and adaptation to our real-world environment. The symbol systems we use in our human society adaptively and dynamically change over time. In the context of artificial intelligence (AI) and cognitive systems, the symbol grounding problem has been regarded as one of the central problems related to symbols. However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered. In this paper, we focus on the symbol emergence problem, addressing not only cognitive dynamics but also the dynamics of symbol systems in society, rather than the symbol grounding problem. We first introduce the notion of a symbol in semiotics from the humanities, to leave the very narrow idea of symbols in symbolic AI. Furthermore, over the years, it became more and more clear that symbol emergence has to be regarded as a multifaceted problem. Therefore, secondly, we review the history of the symbol emergence problem in different fields, including both biological and artificial systems, showing their mutual relations. We summarize the discussion and provide an integrative viewpoint and comprehensive overview of symbol emergence in cognitive systems. Additionally, we describe the challenges facing the creation of cognitive systems that can be part of symbol emergence systems. Copyright © 2018, The Authors. All rights reserved.

关键词： Cognitive systems

来源：评论

学校读者我要写书评

暂无评论

Applications of novel graph theoretic methods to clustering autism spectrum disorders phenotypes 9

Applications of novel graph theoretic methods to clustering ...

引用

9th International Conference on Bioinformatics and Computational Biology, BICOB 2017

作者： Matta, John Nguyen, Thy Ercal, Gunes Obafemi-Ajayi, Tayo Dept. of Computer Science Southern Illinois University Edwardsville EdwardsvilleIL62026 United States Dept. of Computer Science Missouri State University SpringfieldMO65897 United States Engineering Program Missouri State University SpringfieldMO65897 United States

ISBN: (纸本)9781943436071

This paper applies two node-based graph theoretic algorithms to cluster a set of 2680 Autism Spectrum Disorder (ASD) subjects using ASD phenotype features. The two node-based resilience measures are vertex attack tolerance (VAT) and integrity. Analysis of the results performed using internal cluster validation measures and clinical analysis outcome demonstrate the potential usefulness of resilience measure clustering for biomedical datasets.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Authentication pedigree scheme for supply chain

Authentication pedigree scheme for supply chain

引用

Annual IEEE Systems Conference

作者： Manki Min Sunho Lim Yi Liu Hyeun Joong Yoon Computer Science Program Louisiana Tech University Ruston Louisiana Dept. of CS Texas Tech University Lubbock TX Department of EECS South Dakota State University Brookings South Dakota

In this paper, we present a novel idea of multilayer aggregate authentication scheme that can be used in any distribution phase of supply chain for more accurate tracking of packages and for innovative authentication of the hierarchy of packages. With minimal modification cost, our scheme can be adapted to any existing cryptographic hash chain based authentication schemes such as RFID-based scheme. By allowing the aggregate authentication of multiple layers (for example a bigger package and its smaller inner packages) at once, our scheme provides more reliable and accurate way to track the packages and effectively thwarts the counterfeiters at every phase of the supply chain. Our scheme also enables any entity in the entire supply chain including the producers, transporters, distributors, sellers, and even consumers to easily authenticate the authenticity of a package/product along its packaging hierarchy.

关键词： Authentication Packaging Supply chains Radiofrequency identification Nonhomogeneous media Cryptography Aggregates

来源：评论

学校读者我要写书评

暂无评论

Ensemble validation paradigm for intelligent data analysis in autism spectrum disorders

Ensemble validation paradigm for intelligent data analysis i...

引用

IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology (CIBCB)

作者： Thy Nguyen Kerri Nowell Kimberly E. Bodner Tayo Obafemi-Ajayi Computer Science Dept. Missouri State University Springfield MO Thompson Center for Autism & Neurodevelopmental Disorders University of Missouri Columbia MO Engineering Program Missouri State University Springfield MO

Cluster analysis is an important exploratory tool for a broad range of applications including data analysis of biomedical datasets to uncover meaningful subgroups such as in autism spectrum disorder (ASD). For a given clustering algorithm, multiple results can be obtained on the same dataset by varying the algorithm parameters. In biomedical applications, discovering meaningful subgroups, not just the optimal number of clusters, is expedient. It is imperative to develop quality measures capable of identifying optimal partitions for a given dataset. In this paper, we apply varied clustering methods to subgroup an ASD simplex sample based on relevant phenotype features that may uncover meaningful subtypes. We present a detailed cluster validation analysis using an ensemble validation paradigm and visualization techniques. We present a rigorous clinical/behavioral analysis of the top highly ranked results. The evaluation demonstrated that both configurations yielded similar clinical significance results: 2-subgroups configuration with distinct clinical profile.

关键词： Measurement Variable speed drives Clustering algorithms Autism Clustering methods Indexes Data analysis

来源：评论

学校读者我要写书评

暂无评论

OS12.7.A Characterization of intra-tumoral heterogeneity and differential immune activation during malignant progression of meningiomas on single cell level

引用

Neuro-Oncology 2021年第SUPPLEMENT_2期23卷 ii15-ii16页

作者： Blume, C Dogan, H Schweizer, L Wick, W Weller, M Mann, M Kalamarides, M von Deimling, A Schlesner, M Sahm, F CCU Neuropathology German Cancer Research Centre (DKFZ) Heidelberg Germany Dept. of Neuropathology University Hospital Heidelberg Heidelberg Germany Department of Proteomics and Signal Transduction Max Planck Institute of Biochemistry Martinsried Germany German Cancer Research Centre (DKFZ) Heidelberg Germany Department of Neurology and Neurooncology Program National Center for Tumor Diseases Heidelberg University Hospital Heidelberg Germany Department of Neurology Clinical Neuroscience Center University Hospital and University of Zürich Zürich Switzerland NNF Center for Protein Research Faculty of Health Sciences University of Copenhagen Copenhagen Denmark Sorbonne Université and Department of Neurosurgery Pitié Salpêtrière Hospital Paris France Biomedical Informatics Data Mining and Data Analytics Faculty of Applied Computer Science and Medical Faculty University of Augsburg Augsburg Germany

来源：评论

学校读者我要写书评

暂无评论

Roadmap on wavefront shaping and deep imaging in complex media

arXiv

引用

arXiv 2021年

作者： Gigan, Sylvain Katz, Ori de Aguiar, Hilton B. Andresen, Esben Ravn Aubry, Alexandre Bertolotti, Jacopo Bossy, Emmanuel Bouchet, Dorian Brake, Joshua Brasselet, Sophie Bromberg, Yaron Cao, Hui Chaigne, Thomas Cheng, Zhongtao Choi, Wonshik Čižmár, Tomáš Cui, Meng Curtis, Vincent R. Defienne, Hugo Hofer, Matthias Horisaki, Ryoichi Horstmeyer, Roarke Ji, Na LaViolette, Aaron K. Mertz, Jerome Moser, Christophe Mosk, Allard P. Pégard, Nicolas C. Piestun, Rafael Popoff, Sebastien Phillips, David B. Psaltis, Demetri Rahmani, Babak Rigneault, Hervé Rotter, Stefan Tian, Lei Vellekoop, Ivo M. Waller, Laura Wang, Lihong Weber, Timothy Xiao, Sheng Xu, Chris Yamilov, Alexey Yang, Changhuei Yılmaz, Hasan Cornell University United States University of California Berkeley United States Department of Biomedical Engineering Boston University United States Laboratoire Kastler Brossel ENS-Université PSL CNRS Sorbonne Université Collège de France 24 rue Lhomond Paris75005 France Univ. Grenoble Alpes CNRS LIPhy Grenoble38000 France Aix Marseille Univ. CNRS Centrale Marseille Institut Fresnel Marseille France Institute for Basic Science Department of Physics Korea University Korea Republic of Institut Langevin ESPCI PSL University CNRS Paris France Aix Marseille Univ CNRS Centrale Marseille Institut Fresnel MarseilleF-13013 France School of Physics and Astronomy University of Exeter ExeterEX4 4QL United Kingdom Leibniz Institute of Photonic Technology Albert-Einstein-Straße 9 Jena07745 Germany Laboratory of Applied Photonics Devices School of Engineering Ecole Polytechnique Fédérale de Lausanne Lausanne1015 Switzerland Laboratory of Optics School of Engineering Ecole Polytechnique Fédérale de Lausanne Lausanne1015 Switzerland Université de Lille CNRS UMR 8523 PhLAM Laboratoire de Physique des Lasers Atomes et Molécules LilleF-59000 France Department of Electrical and Computer Engineering Boston University BostonMA02215 United States Department of Applied Physical Sciences UNC Chapel Hill United States Department of Electrical Engineering and Computer Sciences UC Berkeley United States Department of Biomedical Engineering UNC Chapel Hill United States UNC Neuroscience Centre UNC Chapel Hill United States Department of Applied Physics Hebrew University of Jerusalem Jerusalem Israel Department of Science and Technology University of Twente Enschede Netherlands University of Tokyo Japan Institute of Scientific Instruments of the Czech Academy of Sciences Královopolská 147 Brno612 64 Czech Republic Dept. of Applied Physics Yale University United States Dept. of Physics Missouri University of Science and Technology United States Bi

The last decade has seen the development of a wide set of tools, such as wavefront shaping, computational or fundamental methods, that allow to understand and control light propagation in a complex medium, such as biological tissues or multimode fibers. A vibrant and diverse community is now working on this field, that has revolutionized the prospect of diffraction-limited imaging at dept. in tissues. This roadmap highlights several key aspects of this fast developing field, and some of the challenges and opportunities ahead. Copyright © 2021, The Authors. All rights reserved.

关键词： Multimode fibers

来源：评论

学校读者我要写书评

暂无评论

The Form of High-Performance Computing: A Survey

引用

IOP Conference Series: Materials science and Engineering 2019年第5期662卷

作者： Priati Assiroj H L H S Warnars R Kosala B Ranti S Supangat A I Kistijantoro E Abdurrachman Binus Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta Information System Dept. Buana Perjuangan University Karawang Computer Science Department BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta Information System Department Bina Nusantara University Jakarta Information System Technology Department Institut Teknologi Bandung School of Electronics Engineering and Informatics Institut Teknologi Bandung

Computational technology is an important thing that needed in the whole of human life. Along with the development of computer technology, there are a significant data created and wait to be processed; we will get more advantages if it well-processed, if not we will see the data explosion, the data is just a useless stack. Research mitigates the other research paper and makes a conclusion and a report by PRISMA method. The development of computer technology will support the development of an organization. Considering any factors in choosing the right and suitable high-performance computer resource due to our organization is a must. The existing high-performance computing forms are Supercomputer, Grid Computing, Cluster Computing, and Cloud Computing. Based on this work, the last form of high-performance computing, Cloud Computing is one of the most used forms thus we mitigate its advantages and disadvantages. Recently, to process this vast data, we must have a high-performance computer and to provide it, this is not a cheap resource.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Viroinformatics-based investigation of SARS-CoV-2 core proteins for potential therapeutic targets

arXiv

引用

arXiv 2020年

作者： Agrawal, Lokesh Poullikkas, Thanasis Eisenhower, Scott Monsanto, Carlo Bakku, Ranjith Kumar Universidad Integral del Caribe y América Latina Kaminda Cas Grandi #79 Curaçao United States Graduate School of Comprehensive Human Sciences University of Tsukuba 1-1-1 Tennodai Tsukuba305-8577 Japan Molecular Neuroscience Unit Okinawa Institute of Science and Technology Graduate University Kunigami-gun Okinawa904-0412 Japan Human Biology School of Integrative and Global Majors University of Tsukuba 1-1-1 Tennodai Tsukuba305-0006 Japan Department of Experimental Pathology Faculty of Medicine University of Tsukuba 2-1-1 Tennodai Tsukuba305-8576 Japan Department of Infection Biology Faculty of Medicine University of Tsukuba 1-1-1 Tennodai Tsukuba305-8575 Japan Research Workgroup Ronin Institute 127 Haddon Place MontclairNJ07043-2314 United States Faculty of Engineering Information and Systems Dept. of Computer Science University of Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki305-8572 Japan University of Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki305-8572 Japan

Due to SARS-CoV-2 (Severe Acute Respiratory Syndrome Coronavirus 2) being a novel virus, there are currently no known effective antiviral drugs capable of slowing its progress. To accelerate the discovery of potential drug candidates, bioinformatics based in silico drug discovery can be applied as a very robust tool. In the present study, more than 60 antiviral drugs already available on the market, were chosen after literature survey. These can be used in clinical trials for the treatment of COVID-19. In this study, these candidate drugs were ranked based on their potential to interact with the Spike protein and RdRp (RNA-dependent RNA polymerase) of SARS-CoV-2. Additionally, the mechanism of their action as well as how the virus infection can utilize Hemoglobin to decrease the oxygen level in blood is explained. Moreover, multiple sequence alignments of the Spike protein with 75 sequences of different viruses from the Orthocoronavirinae subfamily were performed. This gives insight into the evolutionarily conserved domains that can be targeted using drug or antibody treatment. This multidimensional study opens a new layer of understanding about the most effective drug-targetable sites on the Spike protein of SARS-CoV-2. Copyright © 2020, The Authors. All rights reserved.

关键词： Viruses

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：