Siga este link para ver outros tipos de publicações sobre o tema: Computer network architectures.
Artigos de revistas sobre o tema "Computer network architectures"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores artigos de revistas para estudos sobre o assunto "Computer network architectures".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Veja os artigos de revistas das mais diversas áreas científicas e compile uma bibliografia correta.
1
Gudhka, Drashti. "Computer Network." International Journal for Research in Applied Science and Engineering Technology 12, no. 1 (January 31, 2024): 78–87. http://dx.doi.org/10.22214/ijraset.2024.57862.
Texto completo da fonteResumo:
Abstract: This paper presents a comprehensive overview of computer networking, covering fundamental concepts and modern advancements. It explores core networking principles, including models, architectures, and essential layers. Emphasising contemporary trends, it delves into topics like network security (Zero Trust Architecture, AI/ML), Software-Defined Networking (SDN), IoT security challenges, 5G and Mobile Edge Computing (MEC), network performance optimisation, Big Data analytics, and eco-friendly networking strategies. Aimed at students, researchers, and professionals, this overview serves as a valuable resource for understanding both foundational principles and cutting-edge developments in networking.
2
Wang, Yan, and Jun Hui Zheng. "A Well Modularized Computer Network Architecture." Applied Mechanics and Materials 631-632 (September 2014): 902–5. http://dx.doi.org/10.4028/www.scientific.net/amm.631-632.902.
Texto completo da fonteResumo:
By analyzing a variety of computer network architectures, we can find that researchers establish different computer network models from their different starting points and get different computer network architectures by different modularization methods. We establish a well modularized non-layered computer network architecture. This paper compares it with the layered architecture and obtains a conclusion that it is superior to the layered architecture. We have developed two framework prototypes of it. In the one of them we develop some application softwares of TCP/IP, including E-mail, FTP, Web and standard IP telephone, which have been tested by the third-party. It could show the accuracy and easily implemented property of this architecture.
3
DELGADO-FRIAS, JOSE G., STAMATIS VASSILIADIS, and JAMSHID GOSHTASBI. "SEMANTIC NETWORK ARCHITECTURES: AN EVALUATION." International Journal on Artificial Intelligence Tools 01, no. 01 (March 1992): 57–83. http://dx.doi.org/10.1142/s0218213092000132.
Texto completo da fonteResumo:
Semantic networks as a means for knowledge representation and manipulation are used in many artificial intelligence applications. A number of computer architectures, that have been reported for semantic network processing, are presented in this paper. A novel set of evaluation criteria for such semantic network architectures has been developed. Semantic network processing as well as architectural issues are considered in such evaluation criteria. A study of how the reported architectures meet the requirements of each criterion is presented. This set of evaluation criteria is useful for future designs of machines for semantic networks because of its comprehensive range of issues on semantic networks and architectures.
4
Zhang, Xinyu, Vincent C. S. Lee, Jia Rong, Feng Liu, and Haoyu Kong. "Multi-channel convolutional neural network architectures for thyroid cancer detection." PLOS ONE 17, no. 1 (January 21, 2022): e0262128. http://dx.doi.org/10.1371/journal.pone.0262128.
Texto completo da fonteResumo:
Early detection of malignant thyroid nodules leading to patient-specific treatments can reduce morbidity and mortality rates. Currently, thyroid specialists use medical images to diagnose then follow the treatment protocols, which have limitations due to unreliable human false-positive diagnostic rates. With the emergence of deep learning, advances in computer-aided diagnosis techniques have yielded promising earlier detection and prediction accuracy; however, clinicians’ adoption is far lacking. The present study adopts Xception neural network as the base structure and designs a practical framework, which comprises three adaptable multi-channel architectures that were positively evaluated using real-world data sets. The proposed architectures outperform existing statistical and machine learning techniques and reached a diagnostic accuracy rate of 0.989 with ultrasound images and 0.975 with computed tomography scans through the single input dual-channel architecture. Moreover, the patient-specific design was implemented for thyroid cancer detection and has obtained an accuracy of 0.95 for double inputs dual-channel architecture and 0.94 for four-channel architecture. Our evaluation suggests that ultrasound images and computed tomography (CT) scans yield comparable diagnostic results through computer-aided diagnosis applications. With ultrasound images obtained slightly higher results, CT, on the other hand, can achieve the patient-specific diagnostic design. Besides, with the proposed framework, clinicians can select the best fitting architecture when making decisions regarding a thyroid cancer diagnosis. The proposed framework also incorporates interpretable results as evidence, which potentially improves clinicians’ trust and hence their adoption of the computer-aided diagnosis techniques proposed with increased efficiency and accuracy.
5
Yan, Jiamiao. "Application of CNN in computer vision." Applied and Computational Engineering 30, no. 1 (January 22, 2024): 104–10. http://dx.doi.org/10.54254/2755-2721/30/20230081.
Texto completo da fonteResumo:
Today's deep learning continues to be hot, and the application of machine learning can be seen in more and more fields. A neural network model called a Convolutional Neural Network (CNN) was created to imitate the structure of the human brain. It is a convolution operation that maps the relationship between input features and output features to a two-dimensional in the vector space of , the network can effectively process the input data. CNN emerged to solve the computational bottleneck problem faced by traditional networks. This paper discusses the application of the deep learning model CNN in image classification, target detection and face recognition. In these fields, models are continuously proposed, and architectures in each field are constantly emerging. Among them will be the classic architecture of CNN in this field. These classic architectures have their advantages, but there will also be improvements brought about by the shortcomings of the classic architecture. Through the application of these different fields, we can see that CNN-based deep learning can help various fields, and the efficiency will be improved, but it is not perfect and needs continuous improvement.
6
Kaiser, Marcus. "Brain architecture: a design for natural computation." Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 365, no. 1861 (September 13, 2007): 3033–45. http://dx.doi.org/10.1098/rsta.2007.0007.
Texto completo da fonteResumo:
Fifty years ago, John von Neumann compared the architecture of the brain with that of the computers he invented and which are still in use today. In those days, the organization of computers was based on concepts of brain organization. Here, we give an update on current results on the global organization of neural systems. For neural systems, we outline how the spatial and topological architecture of neuronal and cortical networks facilitates robustness against failures, fast processing and balanced network activation. Finally, we discuss mechanisms of self-organization for such architectures. After all, the organization of the brain might again inspire computer architecture.
7
Duan, Qiang. "Intelligent and Autonomous Management in Cloud-Native Future Networks—A Survey on Related Standards from an Architectural Perspective." Future Internet 13, no. 2 (February 5, 2021): 42. http://dx.doi.org/10.3390/fi13020042.
Texto completo da fonteResumo:
Cloud-native network design, which leverages network virtualization and softwarization together with the service-oriented architectural principle, is transforming communication networks to a versatile platform for converged network-cloud/edge service provisioning. Intelligent and autonomous management is one of the most challenging issues in cloud-native future networks, and a wide range of machine learning (ML)-based technologies have been proposed for addressing different aspects of the management challenge. It becomes critical that the various management technologies are applied on the foundation of a consistent architectural framework with a holistic vision. This calls for standardization of new management architecture that supports seamless the integration of diverse ML-based technologies in cloud-native future networks. The goal of this paper is to provide a big picture of the recent developments of architectural frameworks for intelligent and autonomous management for future networks. The paper surveys the latest progress in the standardization of network management architectures including works by 3GPP, ETSI, and ITU-Tand analyzes how cloud-native network design may facilitate the architecture development for addressing management challenges. Open issues related to intelligent and autonomous management in cloud-native future networks are also discussed in this paper to identify some possible directions for future research and development.
8
Rowshanrad, Shiva, Mohamad Reza Parsaei, and Manijeh Keshtgari. "IMPLEMENTING NDN USING SDN: A REVIEW ON METHODS AND APPLICATIONS." IIUM Engineering Journal 17, no. 2 (November 30, 2016): 11–20. http://dx.doi.org/10.31436/iiumej.v17i2.590.
Texto completo da fonteResumo:
In recent years many claims about the limitations of todays’ network architecture, its lack of flexibility and ability to response to ongoing changes and increasing users demands. In this regard, new network architectures are proposed. Software Defined Networking (SDN) is one of these new architectures which centralizes the control of network by separating control plane from data plane. This separation leads to intelligence, flexibility and easier control in computer networks. One of the advantages of this framework is the ability to implement and test new protocols and architectures in actual networks without any concern of interruption.Named Data Networking (NDN) is another paradigm for future network architecture. With NDN the network becomes aware of the content that is providing, rather than just transferring it among end-points. NDN attracts researchers’ attention and known as the potential future of networking and internet. Providing NDN functionalities over SDN is an important requirement to enable the innovation and optimization of network resources. In this paper first we describe about SDN and NDN, and then we introduce methods for implementing NDN using SDN. We also point out the advantages and applications of implementing NDN over SDN.
9
Zkik, Karim, Said EL Hajji, and Ghizlane Orhanou. "A centralized secure plan for detecting and mitigation incidents in hybrid SDN." MATEC Web of Conferences 189 (2018): 10015. http://dx.doi.org/10.1051/matecconf/201818910015.
Texto completo da fonteResumo:
The information technology sector has experienced phenomenal growth during recent years. To follow this development many new technologies have emerged to satisfy the expectations of businesses and customers, such as Cloud Computing, mobility, virtualization, Internet of things and big data. Traditional network cannot longer support this growth and suffers more and more in terms of misconfiguration,management and configurations complexity. Software defined network (SDN) architectures can be considered as a big revolution in the field of computer networks, because they offer a centralized control on infrastructure, services and the applications deployed which facilitate configuration and management on the network. The implementation of this type of architecture is not obvious and requires great expertise and good handling and management of network equipment. To remedy this problem the SDN architectures have evolved towards distributed and hybrid architectures. Despites the advantages of using SDN, security issues remain a real obstacle in front of the deployment of this type of architecture. The centralized architecture of this type of networks makes it vulnerable to several types of attacks and intrusions, and the implementation of security equipment generally causes a decrease in performance and increase latency.
10
Dinn, Neil F. "Network architectures." Future Generation Computer Systems 7, no. 1 (October 1991): 79–89. http://dx.doi.org/10.1016/0167-739x(91)90018-s.
Texto completo da fonte
11
Dovrolis, Constantine, and J. Todd Streelman. "Evolvable network architectures." ACM SIGCOMM Computer Communication Review 40, no. 2 (April 9, 2010): 72–77. http://dx.doi.org/10.1145/1764873.1764886.
Texto completo da fonte
12
Kryukov, Ya V., D. A. Pokamestov, E. V. Rogozhnikov, S. A. Novichkov, and D. V. Lakontsev. "Analysis of Computational Complexity and Processing Time Evaluation of the Protocol Stack in 5G New Radio." Proceedings of Tomsk State University of Control Systems and Radioelectronics 23, no. 3 (September 25, 2020): 31–37. http://dx.doi.org/10.21293/1818-0442-2020-23-3-31-37.
Texto completo da fonteResumo:
Currently, an active deployment of radio access networks for mobile communication systems 5G New Radio is being observed. The architecture of networks is developing rapidly, where significant part of the functions is performed in a virtual cloud space of a personal computer. The computing power of a personal computer must be sufficient to execute network protocols in real time. To reduce the cost of deploying 5G NR networks, the configuration of each remote computer must be optimally matched to the scale of a particular network. Therefore, an urgent direction of research is the assessment of the execution time of the 5G NR protocol stack on various configurations of computers and the development of a mathematical model for data analysis, approximation of dependencies and making recommendations. In this paper, the authors provide an overview of the main 5G NR network architectures, as well as a description of the methods and tools that can be used to estimate the computational complexity of the 5G NR protocol stack. The final section provides an analysis of the computational complexity of the protocol stack, obtained during the experiments by colleagues in partner institutions.
13
Hác, Anna. "Wireless ATM network architectures." International Journal of Network Management 11, no. 3 (May 2001): 161–67. http://dx.doi.org/10.1002/nem.399.
Texto completo da fonte
14
Altukhov, V. G. "Plant disease severity estimation by computer vision methods." Siberian Herald of Agricultural Science 51, no. 2 (June 7, 2021): 107–12. http://dx.doi.org/10.26898/0370-8799-2021-2-13.
Texto completo da fonteResumo:
The first stage results within the framework of the thesis “Investigation of computer vision methods and algorithms in the field of plant diseases detection” are presented. The analysis of the work related to the automatic assessment of plant disease severity was carried out. It was established that for solving problems in this field, convolution neural networks are promising methods, which are currently superior to classical methods of computer vision in terms of accuracy. To assess the severity degree, classification and segmentation architectures of convolutional neural networks are used. Classification architectures are able to take into account disease visual features at different stages of the disease development, but information about the actual affected area is unavailable. On the other hand, solutions based on segmentation architectures provide actual data on the lesion area, but do not grade severity levels according to disease visual features. Based on the result of the research into the application of convolutional neural networks and options for their use, the goal of this study was determined, which is to develop an automatic system capable of determining the lesion area, as well as to take into account disease visual features and the type of immunological reaction of the plant at different stages of disease progress. It is planned to build a system based on the segmentation architecture of a convolutional neural network, which will produce multi-class image segmentation. Such a network is able to divide image pixels into several classes: background, healthy leaf area, affected leaf area. In turn, the class "affected leaf area" will include several subclasses corresponding to the disease visual features at different stages of disease progress.
15
State, Radu. "Review: Network Security Architectures." Queue 3, no. 1 (February 2005): 61. http://dx.doi.org/10.1145/1046931.1046951.
Texto completo da fonte
16
Yuan, Peisen, Yi Sun, and Hengliang Wang. "Heterogeneous Information Network-Based Recommendation with Metapath Search and Memory Network Architecture Search." Mathematics 10, no. 16 (August 12, 2022): 2895. http://dx.doi.org/10.3390/math10162895.
Texto completo da fonteResumo:
Recommendation systems are now widely used on the Internet. In recommendation systems, user preferences are predicted by the interaction of users with products, such as clicks or purchases. Usually, the heterogeneous information network is used to capture heterogeneous semantic information in data, which can be used to solve the sparsity problem and the cold-start problem. In a more complex heterogeneous information network, the types of nodes and edges are very large, so there are lots of types of metagraphs in a complex heterogeneous information network. At the same time, machine learning tasks on heterogeneous information networks have a large number of parameters and neural network architectures that need to be set artificially. The main goal is to find the optimal hyperparameter settings and neural network architectures for the performance of a task in the set of hyperparameter space. To address this problem, we propose a metapath search method for heterogeneous information networks based on a network architecture search, which can search for metapaths that are more suitable for different heterogeneous information networks and recommendation tasks. We conducted experiments on Amazon and Yelp datasets and compared the architecture settings obtained from an automatic search with manually set structures to verify the effectiveness of the algorithm.
17
Khasambiev, I. V., and E. A. Guseva. "Network architectures and protocols of M2M communications." Journal of Physics: Conference Series 2176, no. 1 (June 1, 2022): 012019. http://dx.doi.org/10.1088/1742-6596/2176/1/012019.
Texto completo da fonteResumo:
Abstract The issues of building the architecture of M2M networks and managing M2M services using the capabilities of the IMS platform are considered Introduction. M2M (Machine to Machine) is a complex of technologies that provide automatic interaction between devices (things) without human intervention. The Internet of Things is not a single technology, but a whole system of technological solutions. It is a global network infrastructure, which consists of computer networks of physical objects, the traditional IP Internet, and various devices connecting these networks.
18
Cîrneanu, Andrada-Livia, Dan Popescu, and Dragoș Iordache. "New Trends in Emotion Recognition Using Image Analysis by Neural Networks, a Systematic Review." Sensors 23, no. 16 (August 10, 2023): 7092. http://dx.doi.org/10.3390/s23167092.
Texto completo da fonteResumo:
Facial emotion recognition (FER) is a computer vision process aimed at detecting and classifying human emotional expressions. FER systems are currently used in a vast range of applications from areas such as education, healthcare, or public safety; therefore, detection and recognition accuracies are very important. Similar to any computer vision task based on image analyses, FER solutions are also suitable for integration with artificial intelligence solutions represented by different neural network varieties, especially deep neural networks that have shown great potential in the last years due to their feature extraction capabilities and computational efficiency over large datasets. In this context, this paper reviews the latest developments in the FER area, with a focus on recent neural network models that implement specific facial image analysis algorithms to detect and recognize facial emotions. This paper’s scope is to present from historical and conceptual perspectives the evolution of the neural network architectures that proved significant results in the FER area. This paper endorses convolutional neural network (CNN)-based architectures against other neural network architectures, such as recurrent neural networks or generative adversarial networks, highlighting the key elements and performance of each architecture, and the advantages and limitations of the proposed models in the analyzed papers. Additionally, this paper presents the available datasets that are currently used for emotion recognition from facial expressions and micro-expressions. The usage of FER systems is also highlighted in various domains such as healthcare, education, security, or social IoT. Finally, open issues and future possible developments in the FER area are identified.
19
Marsden, Brian W. "Local Area Network Architectures." Computer Communications 12, no. 2 (April 1989): 107. http://dx.doi.org/10.1016/0140-3664(89)90066-2.
Texto completo da fonte
20
Nafiiyah, Nur. "Identifikasi Tumor Otak Citra MRI dengan Convolutional Neural Network." Jurnal Informatika: Jurnal Pengembangan IT 8, no. 3 (September 17, 2023): 213–19. http://dx.doi.org/10.30591/jpit.v8i3.4985.
Texto completo da fonteResumo:
The science of artificial intelligence and computer vision is beneficial in facilitating the detection of diseases in the medical field. Computer-based disease detection can save time. However, identifying and detecting tumors on MRI images require seriousness and is time-consuming. Due to the diversity of structures in size, shape, and intensity of the image, accuracy is needed in identifying the original organ structure and the diseased one. Previous studies have proposed a method for identifying brain tumors to produce the correct precision. In previous studies, neural network-based methods have good accuracy. We present five Convolutional Neural Network (CNN) architectures for identifying brain tumors (glioma, meningioma, no tumor, and pituitary) on MRI images. This study aims to develop an optimal CNN architecture for identifying tumors. We use the dataset from Kaggle with a total training data of 5712 and testing of 1311. Of the five proposed CNN architectures, architecture c has the highest accuracy of 82.2% with an unlimited number of parameters of 29605060. A good CNN architecture has many convolution layers. We also compare the proposed architecture with CNN transfer learning (Inception, ResNet-50, and VGG16), and with CNN transfer learning architecture, the accuracy is higher than our proposed architecture.
21
P, Shanmugavadivu, Mary Shanthi Rani M, Chitra P, Lakshmanan S, Nagaraja P, and Vignesh U. "Bio-Optimization of Deep Learning Network Architectures." Security and Communication Networks 2022 (September 20, 2022): 1–11. http://dx.doi.org/10.1155/2022/3718340.
Texto completo da fonteResumo:
Deep learning is reaching new heights as a result of its cutting-edge performance in a variety of fields, including computer vision, natural language processing, time series analysis, and healthcare. Deep learning is implemented using batch and stochastic gradient descent methods, as well as a few optimizers; however, this led to subpar model performance. However, there is now a lot of effort being done to improve deep learning’s performance using gradient optimization methods. The suggested work analyses convolutional neural networks (CNN) and deep neural networks (DNN) using several cutting-edge optimizers to enhance the performance of architectures. This work uses specific optimizers (SGD, RMSprop, Adam, Adadelta, etc.) to enhance the performance of designs using different types of datasets for result matching. A thorough report on the optimizers’ performance across a variety of architectures and datasets finishes the study effort. This research will be helpful to researchers in developing their framework and appropriate architecture optimizers. The proposed work involves eight new optimizers using four CNN and DNN architectures. The experimental results exploit breakthrough results for improving the efficiency of CNN and DNN architectures using various datasets.
22
Alekhina, Anna E., Mikhail G. Dorrer, and Alexander G. Ovchinnikov. "Smart eco-friendly refrigerator based on implementation of architectures of convolutional neural networks." E3S Web of Conferences 390 (2023): 03010. http://dx.doi.org/10.1051/e3sconf/202339003010.
Texto completo da fonteResumo:
The article discusses the solution to the problem of choosing the architecture of a convolutional neural network for use in the computer vision of a smart vending refrigerator. Comparative tests decided the architectures of convolutional neural networks YOLOv2, YOLOv3, YOLOv4, Mask R-CNN, and YOLACT ++ on a standard MS COCO dataset, and then on datasets formed from images of typical smart refrigerator products. As a result of comparative tests, the best performance was demonstrated by the YOLOv3 architecture, trained based on a normalized dataset, supplemented with examples with complex intersections of samples without preprocessing examples. The obtained results substantiated the architecture used in computer vision of serially produced "smart" vending machines.
23
Andriyanov, Nikita. "Application of Graph Structures in Computer Vision Tasks." Mathematics 10, no. 21 (October 29, 2022): 4021. http://dx.doi.org/10.3390/math10214021.
Texto completo da fonteResumo:
On the one hand, the solution of computer vision tasks is associated with the development of various kinds of images or random fields mathematical models, i.e., algorithms, that are called traditional image processing. On the other hand, nowadays, deep learning methods play an important role in image recognition tasks. Such methods are based on convolutional neural networks that perform many matrix multiplication operations with model parameters and local convolutions and pooling operations. However, the modern artificial neural network architectures, such as transformers, came to the field of machine vision from natural language processing. Image transformers operate with embeddings, in the form of mosaic blocks of picture and the links between them. However, the use of graph methods in the design of neural networks can also increase efficiency. In this case, the search for hyperparameters will also include an architectural solution, such as the number of hidden layers and the number of neurons for each layer. The article proposes to use graph structures to develop simple recognition networks on different datasets, including small unbalanced X-ray image datasets, widely known the CIFAR-10 dataset and the Kaggle competition Dogs vs Cats dataset. Graph methods are compared with various known architectures and with networks trained from scratch. In addition, an algorithm for representing an image in the form of graph lattice segments is implemented, for which an appropriate description is created, based on graph data structures. This description provides quite good accuracy and performance of recognition. The effectiveness of this approach based, on the descriptors of the resulting segments, is shown, as well as the graph methods for the architecture search.
24
Summers, Kenneth L., Thomas Preston Caudell, Kathryn Berkbigler, Brian Bush, Kei Davis, and Steve Smith. "Graph Visualization for the Analysis of the Structure and Dynamics of Extreme-Scale Supercomputers." Information Visualization 3, no. 3 (July 8, 2004): 209–22. http://dx.doi.org/10.1057/palgrave.ivs.9500079.
Texto completo da fonteResumo:
We are exploring the development and application of information visualization techniques for the analysis of new massively parallel supercomputer architectures. Modern supercomputers typically comprise very large clusters of commodity SMPs interconnected by possibly dense and often non-standard networks. The scale, complexity, and inherent non-locality of the structure and dynamics of this hardware, and the operating systems and applications distributed over them, challenge traditional analysis methods. As part of the á la carte (A Los Alamos Computer Architecture Toolkit for Extreme-Scale Architecture Simulation) team at Los Alamos National Laboratory, who are simulating these new architectures, we are exploring advanced visualization techniques and creating tools to enhance analysis of these simulations with intuitive three-dimensional representations and interfaces. This work complements existing and emerging algorithmic analysis tools. In this paper, we give background on the problem domain, a description of a prototypical computer architecture of interest (on the order of 10,000 processors connected by a quaternary fat-tree communications network), and a presentation of three classes of visualizations that clearly display the switching fabric and the flow of information in the interconnecting network.
25
Bezirganyan, Grigor, and Hayk Akarmazyan. "Improving Differentiable Neural Architecture Search with Sparse Connections and Model Pruning." “Katchar” Collection of Scientific Articles International Scientific-Educational Center NAS RA, no. 1 (July 26, 2022): 203–19. http://dx.doi.org/10.54503/2579-2903-2022.1-203.
Texto completo da fonteResumo:
Neural networks have contributed to many breakthroughs across several disciplines. Their ease of use and scalability have motivated the development of many techniques in computer vision, natural language processing, audio analysis, etc. The neural network architecture plays a dominant role in its performance, and there have been many advances on designs and strategies for defining efficient neural networks. However, manually tuning neural architectures requires a significant amount of time and expert knowledge. To overcome the difficulty of manually setting up the architecture for a neural network, Neural Architecture Search (NAS) has gained popularity. NAS methods involve three general dimensions, namely search space, search strategies, and performance estimation strategies [1]. Different approaches vary in these dimensions.
26
Broustis, Ioannis, and Michalis Faloutsos. "Routing in Vehicular Networks: Feasibility, Modeling, and Security." International Journal of Vehicular Technology 2008 (April 21, 2008): 1–8. http://dx.doi.org/10.1155/2008/267513.
Texto completo da fonteResumo:
Vehicular networks are sets of surface transportation systems that have the ability to communicate with each other. There are several possible network architectures to organize their in-vehicle computing systems. Potential schemes may include vehicle-to-vehicle ad hoc networks, wired backbone with wireless last hops, or hybrid architectures using vehicle-to-vehicle communications to augment roadside communication infrastructures. Some special properties of these networks, such as high mobility, network partitioning, and constrained topology, differentiate them from other types of wireless networks. We provide an in-depth discussion on the important studies related to architectural design and routing for such networks. Moreover, we discuss the major security concerns appearing in vehicular networks.
27
Al Bataineh, Ali, Devinder Kaur, Mahmood Al-khassaweneh, and Esraa Al-sharoa. "Automated CNN Architectural Design: A Simple and Efficient Methodology for Computer Vision Tasks." Mathematics 11, no. 5 (February 24, 2023): 1141. http://dx.doi.org/10.3390/math11051141.
Texto completo da fonteResumo:
Convolutional neural networks (CNN) have transformed the field of computer vision by enabling the automatic extraction of features, obviating the need for manual feature engineering. Despite their success, identifying an optimal architecture for a particular task can be a time-consuming and challenging process due to the vast space of possible network designs. To address this, we propose a novel neural architecture search (NAS) framework that utilizes the clonal selection algorithm (CSA) to automatically design high-quality CNN architectures for image classification problems. Our approach uses an integer vector representation to encode CNN architectures and hyperparameters, combined with a truncated Gaussian mutation scheme that enables efficient exploration of the search space. We evaluated the proposed method on six challenging EMNIST benchmark datasets for handwritten digit recognition, and our results demonstrate that it outperforms nearly all existing approaches. In addition, our approach produces state-of-the-art performance while having fewer trainable parameters than other methods, making it low-cost, simple, and reusable for application to multiple datasets.
28
Fethellah, Nour El Houda, Hafida Bouziane, and Abdallah Chouarfia. "NECS-based Cache Management in the Information Centric Networking." International Journal of Interactive Mobile Technologies (iJIM) 15, no. 21 (November 9, 2021): 172. http://dx.doi.org/10.3991/ijim.v15i21.20011.
Texto completo da fonteResumo:
The Information Centric Networking ICN architectures are proposed to overcome the problems of the actual internet architecture. One of the main straight points of the ICN architectures is the in-network caching. The ICN performance is influenced by efficiency of the adopted caching strategy which manages the contents in the network and decides where caching them. However, the major issue which faces the caching strategies in the ICN architectures is the strategic election of the cache routers to store the data through its delivery path. This will reduce congestion, optimize the distance between the consumers and the required data furthermore improve latency and alleviate the viral load on the servers. In this paper, we propose a new efficient caching strategy for the Named Data Networking architecture NDN named NECS which is the most promising architecture between all the ICN architectures. The proposed strategy reduces the traffic redundancy, eliminates the useless replication of contents and improves the replay time for users due to the strategic position of cache routers. Besides, we evaluate the performance of this proposed strategy and we compare it with three other NDN caching strategies, using the simulator network environment NdnSIM. On the basis of the simulations carried out, we obtained interesting and convincing results.
29
Xia, Chengpeng, Yawen Chen, Haibo Zhang, Hao Zhang, Fei Dai, and Jigang Wu. "Efficient neural network accelerators with optical computing and communication." Computer Science and Information Systems, no. 00 (2022): 66. http://dx.doi.org/10.2298/csis220131066x.
Texto completo da fonteResumo:
Conventional electronic Artificial Neural Networks (ANNs) accelerators focus on architecture design and numerical computation optimization to improve the training efficiency. However, these approaches have recently encountered bottlenecks in terms of energy efficiency and computing performance, which leads to an increase interest in photonic accelerator. Photonic architectures with low energy consumption, high transmission speed and high bandwidth have been considered as an important role for generation of computing architectures. In this paper, to provide a better understanding of optical technology used in ANN acceleration, we present a comprehensive review for the efficient photonic computing and communication in ANN accelerators. The related photonic devices are investigated in terms of the application in ANNs acceleration, and a classification of existing solutions is proposed that are categorized into optical computing acceleration and optical communication acceleration according to photonic effects and photonic architectures. Moreover, we discuss the challenges for these photonic neural network acceleration approaches to highlight the most promising future research opportunities in this field.
30
NAKANO, KOJI. "A BIBLIOGRAPHY OF PUBLISHED PAPERS ON DYNAMICALLY RECONFIGURABLE ARCHITECTURES." Parallel Processing Letters 05, no. 01 (March 1995): 111–24. http://dx.doi.org/10.1142/s0129626495000102.
Texto completo da fonteResumo:
A dynamically reconfigurable architecture is a parallel computer architecture that supports a physical switching of communication patterns during a computation. Basically, the dynamically reconfigurable architecture consists of locally controllable switches, which enables flexible-connection patterns of the network. The bibliography attempts to classify published papers on dynamically reconfigurable architectures according to the problems that are dealt with.
31
Shin, Jiyong, Kyongseok Park, and Dae-Ki Kang. "TA-DARTS: Temperature Annealing of Discrete Operator Distribution for Effective Differential Architecture Search." Applied Sciences 13, no. 18 (September 8, 2023): 10138. http://dx.doi.org/10.3390/app131810138.
Texto completo da fonteResumo:
In the realm of machine learning, the optimization of hyperparameters and the design of neural architectures entail laborious and time-intensive endeavors. To address these challenges, considerable research effort has been directed towards Automated Machine Learning (AutoML), with a focus on enhancing these inherent inefficiencies. A pivotal facet of this pursuit is Neural Architecture Search (NAS), a domain dedicated to the automated formulation of neural network architectures. Given the pronounced impact of network architecture on neural network performance, NAS techniques strive to identify architectures that can manifest optimal performance outcomes. A prominent algorithm in this area is Differentiable Architecture Search (DARTS), which transforms discrete search spaces into continuous counterparts using gradient-based methodologies, thereby surpassing prior NAS methodologies. Notwithstanding DARTS’ achievements, a discrepancy between discrete and continuously encoded architectures persists. To ameliorate this disparity, we propose TA-DARTS in this study—a temperature annealing technique applied to the Softmax function, utilized for encoding the continuous search space. By leveraging temperature values, architectural weights are judiciously adjusted to alleviate biases in the search process or to align resulting architectures more closely with discrete values. Our findings exhibit advancements over the original DARTS methodology, evidenced by a 0.07%p enhancement in validation accuracy and a 0.16%p improvement in test accuracy on the CIFAR-100 dataset. Through systematic experimentation on benchmark datasets, we establish the superiority of TA-DARTS over the original mixed operator, thereby underscoring its efficacy in automating neural architecture design.
32
Akbar, F., A. Ghosh, S. Young, S. Akhter, Z. Ahmad Dar, V. Ansari, M. V. Ascencio, et al. "Vertex finding in neutrino-nucleus interaction: a model architecture comparison." Journal of Instrumentation 17, no. 08 (August 1, 2022): T08013. http://dx.doi.org/10.1088/1748-0221/17/08/t08013.
Texto completo da fonteResumo:
Abstract We compare different neural network architectures for machine learning algorithms designed to identify the neutrino interaction vertex position in the MINERvA detector. The architectures developed and optimized by hand are compared with the architectures developed in an automated way using the package “Multi-node Evolutionary Neural Networks for Deep Learning” (MENNDL), developed at Oak Ridge National Laboratory. While the domain-expert hand-tuned network was the best performer, the differences were negligible and the auto-generated networks performed as well. There is always a trade-off between human, and computer resources for network optimization and this work suggests that automated optimization, assuming resources are available, provides a compelling way to save significant expert time.
33
Bhatt, Dulari, Chirag Patel, Hardik Talsania, Jigar Patel, Rasmika Vaghela, Sharnil Pandya, Kirit Modi, and Hemant Ghayvat. "CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope." Electronics 10, no. 20 (October 11, 2021): 2470. http://dx.doi.org/10.3390/electronics10202470.
Texto completo da fonteResumo:
Computer vision is becoming an increasingly trendy word in the area of image processing. With the emergence of computer vision applications, there is a significant demand to recognize objects automatically. Deep CNN (convolution neural network) has benefited the computer vision community by producing excellent results in video processing, object recognition, picture classification and segmentation, natural language processing, speech recognition, and many other fields. Furthermore, the introduction of large amounts of data and readily available hardware has opened new avenues for CNN study. Several inspirational concepts for the progress of CNN have been investigated, including alternative activation functions, regularization, parameter optimization, and architectural advances. Furthermore, achieving innovations in architecture results in a tremendous enhancement in the capacity of the deep CNN. Significant emphasis has been given to leveraging channel and spatial information, with a depth of architecture and information processing via multi-path. This survey paper focuses mainly on the primary taxonomy and newly released deep CNN architectures, and it divides numerous recent developments in CNN architectures into eight groups. Spatial exploitation, multi-path, depth, breadth, dimension, channel boosting, feature-map exploitation, and attention-based CNN are the eight categories. The main contribution of this manuscript is in comparing various architectural evolutions in CNN by its architectural change, strengths, and weaknesses. Besides, it also includes an explanation of the CNN’s components, the strengths and weaknesses of various CNN variants, research gap or open challenges, CNN applications, and the future research direction.
34
Korchagin, Valeriy Dmitrievich. "Analysis of modern SOTA-architectures of artificial neural networks for solving problems of image classification and object detection." Программные системы и вычислительные методы, no. 4 (April 2023): 73–87. http://dx.doi.org/10.7256/2454-0714.2023.4.69306.
Texto completo da fonteResumo:
The scientific research is focused on conducting a study of current artificial neural network architectures in order to highlight the advantages and disadvantages of current approaches. The relevance of the research relies on the growing interest in machine learning technologies and regular improvement of computer vision algorithms.Within the scope of this paper, an analytical study of the advantages and disadvantages of existing solutions has been conducted and advanced SOTA architectures have been reviewed. The most effective approaches to improve the accuracy of basic models have been studied. The number of parameters used, the size of the training sample, the accuracy of the model, its size, adaptability, complexity and the required computational resources for training a single architecture were determined.Prospects for further research in the field of hybridization of convolutional neural networks and visual transformers are revealed, and a new solution for building a complex neural network architecture is proposed.In the framework of the present research work, a detailed analysis of the internal structure of the most effective neural network architectures.Plots of the accuracy dependence on the number of parameters used in the model and the size of the training sample are plotted. The conducted comparative analysis of the efficiency of the considered solutions allowed to single out the most effective methods and technologies for designing artificial neural network architectures. A novel method focused on creating a complex adaptive model architecture that can be dynamically tuned depending on an input set of parameters is proposed, representing a potentially significant contribution to the field of adaptive neural network design.
35
Sanjar, Karshiev, Olimov Bekhzod, Jaeil Kim, Jaesoo Kim, Anand Paul, and Jeonghong Kim. "Improved U-Net: Fully Convolutional Network Model for Skin-Lesion Segmentation." Applied Sciences 10, no. 10 (May 25, 2020): 3658. http://dx.doi.org/10.3390/app10103658.
Texto completo da fonteResumo:
The early and accurate diagnosis of skin cancer is crucial for providing patients with advanced treatment by focusing medical personnel on specific parts of the skin. Networks based on encoder–decoder architectures have been effectively implemented for numerous computer-vision applications. U-Net, one of CNN architectures based on the encoder–decoder network, has achieved successful performance for skin-lesion segmentation. However, this network has several drawbacks caused by its upsampling method and activation function. In this paper, a fully convolutional network and its architecture are proposed with a modified U-Net, in which a bilinear interpolation method is used for upsampling with a block of convolution layers followed by parametric rectified linear-unit non-linearity. To avoid overfitting, a dropout is applied after each convolution block. The results demonstrate that our recommended technique achieves state-of-the-art performance for skin-lesion segmentation with 94% pixel accuracy and a 88% dice coefficient, respectively.
36
Xie, Xiaoying, and Qitong Wang. "Parameterization of Chinese Ancient Architecture on the Basis of Modulo Relationships." SHS Web of Conferences 171 (2023): 03031. http://dx.doi.org/10.1051/shsconf/202317103031.
Texto completo da fonteResumo:
Contemporary systems are trending toward 3D computer-aided design systems that integrate, network, and exhibit intelligence. The integration of parametric technology with ancient Chinese architecture can enhance the efficiency and quality of managing information on ancient buildings, thereby expanding the application scenarios of ancient architectural information models. By analyzing the construction characteristics of ancient Chinese carpentry work and modular systems, this research outlines the logic and methods for generating Chinese ancient architecture. The program’s parametric technology allows for adjusting variable parameters to produce carpentry work structures of varying scales and forms. Furthermore, this research establishes a library of parametric 3D components for ancient architecture, which can simplify the design process of contemporary antique architecture. Additionally, the parametrization of Chinese ancient architectures can function as an auxiliary tool for maintenance and repair techniques, serving as a storage mechanism for whole-life cycle information. This can enable the digital archiving of component information and model entities in an informative manner for managing existing ancient architectures.
37
Freeman, Donald T. "Computer Applications in Otolaryngology: Computer Recognition of Brain Stem Auditory Evoked Potential Wave V by a Neural Network." Annals of Otology, Rhinology & Laryngology 101, no. 9 (September 1992): 782–90. http://dx.doi.org/10.1177/000348949210100913.
Texto completo da fonteResumo:
A neural network simulator was used for the recognition of the presence and location of the peak of wave V of the brain stem auditory evoked potential (BAEP) test. Waveforms selected from BAEPs performed in the last 4 years at the University of Pittsburgh Presbyterian University Hospital were digitized and sampled, and the resulting amplitudes were normalized. A training set was composed of the waveforms resulting from the stimulation of 50 ears. The normalized amplitudes were used as the initial activation values for the networks. The desired outputs (the target locations for wave V) were represented in the output layer by setting the output element, which corresponded to the target location and its immediate neighbors, to high activation levels, and all the remaining output units to zero activity. Two network architectures, differing only in the hidden unit layer, with 40 and 16 hidden units, respectively, were trained by using standard back-propagation. Several trials from different starting points were performed for each architecture. The best network, found after 60 epochs (3,000 presentations), was able to correctly identify 17 of 20 cases (85%) from a set of test cases that were independent from the training set.
38
Guesmi, Tawfik, Anwar Kalghoum, Badr M. Alshammari, Haitham Alsaif, and Ahmed Alzamil. "Leveraging Software-Defined Networking Approach for Future Information-Centric Networking Enhancement." Symmetry 13, no. 3 (March 9, 2021): 441. http://dx.doi.org/10.3390/sym13030441.
Texto completo da fonteResumo:
Information-centric networking (ICN) has been developed as a potential candidate for future networks. In this model, users are provided with content rather than communication channels between the different hosts. The ICN network has several problems such as scalability issues and bandwidth consumption. However, software-defined networking (SDN) has been proposed to improve the networking architectures. The goal of our paper is to propose a new approach to named-data networking (NDN) based on the paradigm of SDN. Our work introduces various research studies carried out in the SDN and ICN contexts. We first present the SDN architecture. Then, we focus on work that combines ICN and SDN architectures. Finally, we show the effects of using the SDN architecture on the named-data network (NDN). Our experimental results show that the use of the SDN architecture has a positive effect on NDN network performance.
39
Sharp, Duane E. "Network Architectures and Performance." Information Systems Management 15, no. 2 (March 1998): 7–12. http://dx.doi.org/10.1201/1078/43184.15.2.19980301/31113.2.
Texto completo da fonte
40
Gebizlioglu, Osman S., Vijay Jain, and John Spencer. "Optical network architectures [Series Editorial]." IEEE Communications Magazine 51, no. 5 (May 2013): 116–17. http://dx.doi.org/10.1109/mcom.2013.6515055.
Texto completo da fonte
41
Zemrane, Hamza, Youssef Baddi, and Abderrahim Hasbi. "Routing Communication Inside Ad Hoc Drones Network." International Journal of Interactive Mobile Technologies (iJIM) 15, no. 17 (September 6, 2021): 192. http://dx.doi.org/10.3991/ijim.v15i17.19179.
Texto completo da fonteResumo:
The world knows a constant development of technology applied in different sectors of activities: health, factories, homes, transportation, and others, one of the big axes that take a lot of attention today is the drone’s field. To communicate information a fleet of drones can use different communication architectures: centralized communication architecture, satellite communication architecture, cellular network communication architecture and a specific AdHoc communication architecture called the UAANET drones architecture. In our work we focused specifically on the routing of information inside the UAANET where we analyze and compare the performances of the reactive protocol AODV and the proactive protocol OLSR, when the UAANET use an applications based on the HTTP protocol, the FTP protocol, the database queries, voice application, and video conferencing application.
42
Suganuma, Masanori, Masayuki Kobayashi, Shinichi Shirakawa, and Tomoharu Nagao. "Evolution of Deep Convolutional Neural Networks Using Cartesian Genetic Programming." Evolutionary Computation 28, no. 1 (March 2020): 141–63. http://dx.doi.org/10.1162/evco_a_00253.
Texto completo da fonteResumo:
The convolutional neural network (CNN), one of the deep learning models, has demonstrated outstanding performance in a variety of computer vision tasks. However, as the network architectures become deeper and more complex, designing CNN architectures requires more expert knowledge and trial and error. In this article, we attempt to automatically construct high-performing CNN architectures for a given task. Our method uses Cartesian genetic programming (CGP) to encode the CNN architectures, adopting highly functional modules such as a convolutional block and tensor concatenation, as the node functions in CGP. The CNN structure and connectivity, represented by the CGP, are optimized to maximize accuracy using the evolutionary algorithm. We also introduce simple techniques to accelerate the architecture search: rich initialization and early network training termination. We evaluated our method on the CIFAR-10 and CIFAR-100 datasets, achieving competitive performance with state-of-the-art models. Remarkably, our method can find competitive architectures with a reasonable computational cost compared to other automatic design methods that require considerably more computational time and machine resources.
43
Le, Nam Tuan, Mohammad Arif Hossain, Amirul Islam, Do-yun Kim, Young-June Choi, and Yeong Min Jang. "Survey of Promising Technologies for 5G Networks." Mobile Information Systems 2016 (2016): 1–25. http://dx.doi.org/10.1155/2016/2676589.
Texto completo da fonteResumo:
As an enhancement of cellular networks, the future-generation 5G network can be considered an ultra-high-speed technology. The proposed 5G network might include all types of advanced dominant technologies to provide remarkable services. Consequently, new architectures and service management schemes for different applications of the emerging technologies need to be recommended to solve issues related to data traffic capacity, high data rate, and reliability for ensuring QoS. Cloud computing, Internet of things (IoT), and software-defined networking (SDN) have become some of the core technologies for the 5G network. Cloud-based services provide flexible and efficient solutions for information and communications technology by reducing the cost of investing in and managing information technology infrastructure. In terms of functionality, SDN is a promising architecture that decouples control planes and data planes to support programmability, adaptability, and flexibility in ever-changing network architectures. However, IoT combines cloud computing and SDN to achieve greater productivity for evolving technologies in 5G by facilitating interaction between the physical and human world. The major objective of this study provides a lawless vision on comprehensive works related to enabling technologies for the next generation of mobile systems and networks, mainly focusing on 5G mobile communications.
44
Bashar, Dr Abul. "SURVEY ON EVOLVING DEEP LEARNING NEURAL NETWORK ARCHITECTURES." December 2019 2019, no. 2 (December 14, 2019): 73–82. http://dx.doi.org/10.36548/jaicn.2019.2.003.
Texto completo da fonteResumo:
The deep learning being a subcategory of the machine learning follows the human instincts of learning by example to produce accurate results. The deep learning performs training to the computer frame work to directly classify the tasks from the documents available either in the form of the text, image, or the sound. Most often the deep learning utilizes the neural network to perform the accurate classification and is referred as the deep neural networks; one of the most common deep neural networks used in a broader range of applications is the convolution neural network that provides an automated way of feature extraction by learning the features directly from the images or the text unlike the machine learning that extracts the features manually. This enables the deep learning neural networks to have a state of art accuracy that mostly expels even the human performance. So the paper is to present the survey on the deep learning neural network architectures utilized in various applications for having an accurate classification with an automated feature extraction.
45
Thompson, Lionel R. "Local area network architectures." Microprocessors and Microsystems 13, no. 1 (January 1989): 64. http://dx.doi.org/10.1016/0141-9331(89)90040-9.
Texto completo da fonte
46
Thodberg, Hans Henrik. "IMPROVING GENERALIZATION OF NEURAL NETWORKS THROUGH PRUNING." International Journal of Neural Systems 01, no. 04 (January 1991): 317–26. http://dx.doi.org/10.1142/s0129065791000352.
Texto completo da fonteResumo:
A technique for constructing neural network architectures with better ability to generalize is presented under the name Ockham's Razor: several networks are trained and then pruned by removing connections one by one and retraining. The networks which achieve fewest connections generalize best. The method is tested on a classification of bit strings (the contiguity problem): the optimal architecture emerges, resulting in perfect generalization. The internal representation of the network changes substantially during the retraining, and this distinguishes the method from previous pruning studies.
47
Sesha Saiteja, Maddula N. V., K. Sai Sumanth Reddy, D. Radha, and Minal Moharir. "Multi-Core Architecture and Network on Chip: Applications and Challenges." Journal of Computational and Theoretical Nanoscience 17, no. 1 (January 1, 2020): 239–45. http://dx.doi.org/10.1166/jctn.2020.8657.
Texto completo da fonteResumo:
Technology improves performance and reduces in size day by day. Reduction in size can increase the density and which in turn can improve the performance. These statements suit very well for the computer architecture improvement. The whole System on Chip (SoC) brought the concept of multiple cores on a single chip. The multi-core or many-core architectures are the future of computing. Technology has improved in reducing the size and increasing the density, but improving the performance to an expectation of including more cores is a challenge of many-core technology. Utilization of all cores and improving the performance of execution by these cores are the challenges to be addressed in a many-core technology. This paper discusses the basics of many core architecture, comparison and applications. Further, it covers the basics of Network on Chip (NoC), architectural components, and various views of current Network on Chip research problems. Research problems include improving the performance of communication by avoiding congested path in routing.
48
Chen, Chang Wen, and Yu Wang. "Chain-Type Wireless Sensor Network for Monitoring Long Range Infrastructures: Architecture and Protocols." International Journal of Distributed Sensor Networks 4, no. 4 (October 1, 2008): 287–314. http://dx.doi.org/10.1080/15501320701260261.
Texto completo da fonteResumo:
We present in this paper an investigation of a special class of wireless sensor networks for monitoring critical infrastructures that may extend for hundreds of miles in distances. Such networks are fundamentally different from traditional sensor networks in that the sensor nodes in this class of networks are deployed along narrowly elongated geographical areas and form a chain-type topology. Based on careful analysis of existing sensor network architectures, we first demonstrate the need to develop new architecture and networking protocols to match the unique topology of chain-type sensor networks. We then propose hierarchical network architecture that consists of clusters of sensor nodes to enable the chain-type sensor networks to be scalable to cover typically long range infrastructures with tolerable delay in network-wide data collection. To maintain energy efficient operations and maximize the lifetime for such a chain-type sensor network, we devise a smart strategy for the deployment of cluster heads. Protocols for network initialization and seamless operations of the chain-type sensor networks are also developed to match the proposed hierarchical architecture and cluster head deployment strategy. Simulations have been carried out to verify the performance of the hierarchical architecture, the smart node deployment strategy, and the corresponding network initialization and operation protocols.
49
Dautel, Alexander Jakob, Wolfgang Karl Härdle, Stefan Lessmann, and Hsin-Vonn Seow. "Forex exchange rate forecasting using deep recurrent neural networks." Digital Finance 2, no. 1-2 (March 27, 2020): 69–96. http://dx.doi.org/10.1007/s42521-020-00019-x.
Texto completo da fonteResumo:
Abstract Deep learning has substantially advanced the state of the art in computer vision, natural language processing, and other fields. The paper examines the potential of deep learning for exchange rate forecasting. We systematically compare long short-term memory networks and gated recurrent units to traditional recurrent network architectures as well as feedforward networks in terms of their directional forecasting accuracy and the profitability of trading model predictions. Empirical results indicate the suitability of deep networks for exchange rate forecasting in general but also evidence the difficulty of implementing and tuning corresponding architectures. Especially with regard to trading profit, a simpler neural network may perform as well as if not better than a more complex deep neural network.
50
Vitevitch, Michael S., Leo Niehorster-Cook, and Sasha Niehorster-Cook. "Exploring How Phonotactic Knowledge Can Be Represented in Cognitive Networks." Big Data and Cognitive Computing 5, no. 4 (September 23, 2021): 47. http://dx.doi.org/10.3390/bdcc5040047.
Texto completo da fonteResumo:
In Linguistics and Psycholinguistics, phonotactics refers to the constraints on individual sounds in a given language that restrict how those sounds can be ordered to form words in that language. Previous empirical work in Psycholinguistics demonstrated that phonotactic knowledge influenced how quickly and accurately listeners retrieved words from that part of memory known as the mental lexicon. In the present study, we used three computer simulations to explore how three different cognitive network architectures could account for the previously observed effects of phonotactics on processing. The results of Simulation 1 showed that some—but not all—effects of phonotactics could be accounted for in a network where nodes represent words and edges connect words that are phonologically related to each other. In Simulation 2, a different network architecture was used to again account for some—but not all—effects of phonotactics and phonological neighborhood density. A bipartite network was used in Simulation 3 to account for many of the previously observed effects of phonotactic knowledge on spoken word recognition. The value of using computer simulations to explore different network architectures is discussed.