Výsledky vyhľadávania - neural network with encoder-((decoder architecture) OR (design architecture))~

An intelligent speech enhancement model using enhanced heuristic-based residual convolutional neural network with encoder-decoder architecture.

Autori: Balasubrahmanyam, M. Valarmathi, R. S.

Zdroj: International Journal of Speech Technology; Sep2024, Vol. 27 Issue 3, p637-656, 20p

Predmety: CONVOLUTIONAL neural networks, INTELLIGIBILITY of speech, SPEECH perception, SPEECH enhancement, HEARING aids, DEEP learning, SUPERVISED learning, SPEECH

An intelligent speech enhancement model using enhanced heuristic-based residual convolutional neural network with encoder-decoder architecture

Autori: M. Balasubrahmanyam R. S. Valarmathi

Zdroj: International Journal of Speech Technology. 27:637-656

Exhale-Focused Thermal Image Segmentation Using Optical Flow-Based Frame Filtering and Transformer-Aided Deep Networks.

Autori: Lee, Do-Kyeong Shin, Jae-Sung Choi, Jae-Sung a ďalší

Zdroj: Bioengineering (Basel); May2025, Vol. 12 Issue 5, p542, 17p

Predmety: CONVOLUTIONAL neural networks, THERMOGRAPHY, TRANSFORMER models, IMAGE segmentation, COVID-19 pandemic, OPTICAL flow

Design and Implementation of an Intelligent Web Service Agent Based on Seq2Seq and Website Crawler.

Autori: Hsih, Mei-Hua Yang, Jian-Xin Hsieh, Chen-Chiung

Zdroj: Information. Dec2024, Vol. 15 Issue 12, p818. 19p.

Predmety: *Artificial neural networks, *Natural language processing, *Internet content, *Web services, Online social networks, Intelligent personal assistants

On the use of stochastic logic for nonlinear circuits and systems

Autori: Camps Pascual, Oscar Vicente

Thesis Advisors: Picos Gayà, Rodrigo, Stavrinides, Stavros G.

Zdroj: TDX (Tesis Doctorals en Xarxa)

Predmety: Computación estocástica, Memristores, Sistemas no lineales, Computación Estocástica

Time: 621.3

Popis súboru: application/pdf

Prístupová URL adresa: http://hdl.handle.net/10803/688339

Online encoder-decoder anomaly detection using encoder-decoder architecture with novel self-configuring neural networks & pure linear genetic programming for embedded systems

Autori: Kasparaviciute, Gabriele Thelin, Malin Nordin, Peter a ďalší

Zdroj: 11th International Joint Conference on Computational Intelligence, IJCCI 2019, Vienna, Austria IJCCI 2019 - Proceedings of the 11th International Joint Conference on Computational Intelligence. :163-171

Predmety: Neural network, Encoder-decoder, Evolutionary algorithm, Genetic algorithm, Embedded, Self-configuring, Anomaly detection, Linear genetic programming

Popis súboru: electronic

Prístupová URL adresa: https://research.chalmers.se/publication/519597
https://research.chalmers.se/publication/513654
https://research.chalmers.se/publication/519597/file/519597_Fulltext.pdf

Convolutional neural network based encoder-decoder architectures for semantic segmentation of plants.

Autori: Kolhar, Shrikrishna Jagtap, Jayant

Zdroj: Ecological Informatics. Sep2021, Vol. 64, pN.PAG-N.PAG. 1p.

Predmety: Convolutional neural networks, Image segmentation, Plant anatomy, Crop yields, Tobacco growing

Encoder-Decoder Architecture for Image Steganography using Skip Connections.

Autori: Kumar, Akshay Rani, Rajneesh Singh, Samayveer

Zdroj: Procedia Computer Science. 2023, Vol. 218, p1122-1131. 10p.

Predmety: Cryptography, Feature extraction, Technological innovations, Data security, Signal-to-noise ratio, Convolutional neural networks

Time-Series Forecasting Based on Multi-Layer Attention Architecture.

Autori: Na Wang Xianglian Zhao

Zdroj: KSII Transactions on Internet & Information Systems. Jan2024, Vol. 18 Issue 1, p1-14. 14p.

Predmety: Artificial neural networks, Transformer models, Vernacular architecture, Time series analysis, Current transformers (Instrument transformer)

Analysis of the effectiveness of two different loss functions in training a neural network in lung image reconstruction using impedance tomography

Autori: Malgorzata Lalak-Dybała Barbara Stefaniak Paweł Olszewski

Zdroj: Journal of Modern Science, Vol 57, Iss 3, Pp 594-608 (2024)

Predmety: 0301 basic medicine, neural network with encoder-decoder architecture, 03 medical and health sciences, resnet, 0202 electrical engineering, electronic engineering, information engineering, convolutional neural network, Social Sciences, 02 engineering and technology, lung reconstruction, electrical impedance tomography

Prístupová URL adresa: https://doaj.org/article/080fe2c0e5ff4f89b9924bad2ae2f2e4

Towards Practical Neural Image Compression

Autori: Yang, Fei

Thesis Advisors: Herranz, Luis, Mozerov, Mikhail G., Cheng, Yongmei

Zdroj: TDX (Tesis Doctorals en Xarxa)

Predmety: Compressió d'imatges neuronals, Compresión de imágenes neuronales, Neuronal image compression, Compressió de videos neuronals, Compresión de videos neuronales, Neural video compression, Aprenentatge profund, Aprendizaje profundo, Deep learning, Ciències Experimentals

Popis súboru: application/pdf

Prístupová URL adresa: http://hdl.handle.net/10803/675178

Recurrent and Concurrent Prediction of Longitudinal Progression of Stargardt Atrophy and Geographic Atrophy towards Comparative Performance on Optical Coherence Tomography as on Fundus Autofluorescence.

Autori: Mishra, Zubin Wang, Ziyuan Chris Xu, Emily a ďalší

Zdroj: Applied Sciences (2076-3417); Sep2024, Vol. 14 Issue 17, p7773, 16p

Predmety: CONVOLUTIONAL neural networks, ARTIFICIAL neural networks, OPTICAL coherence tomography, DRUG efficacy, THREE-dimensional imaging

CovSegNet: A Multi Encoder-Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans.

Autori: Mahmud, Tanvir Rahman, Md Fattah, Shaikh a ďalší

Zdroj: IEEE Transactions on Artificial Intelligence. 2(3)

Predmety: Artificial intelligence (AI), biomedical imaging, computer aided analysis, image segmentation, neural networks

Popis súboru: application/pdf

Prístupová URL adresa: https://escholarship.org/uc/item/51g6b93g
https://escholarship.org/content/qt51g6b93g/qt51g6b93g.pdf

WaferSegClassNet - A light-weight network for classification and segmentation of semiconductor wafer defects.

Autori: Nag, Subhrajit Makwana, Dhruv R, Sai Chandra Teja a ďalší

Zdroj: Computers in Industry. Nov2022, Vol. 142, pN.PAG-N.PAG. 1p.

Predmety: *ARTIFICIAL intelligence, SEMICONDUCTOR wafers, CONVOLUTIONAL neural networks, SEMICONDUCTOR defects, COMPUTER vision, SEMICONDUCTOR design

Attention-adaptive and deformable convolutional modules for dynamic scene deblurring.

Autori: Chen, Lei Sun, Quansen Wang, Fanhai

Zdroj: Information Sciences. Feb2021, Vol. 546, p368-377. 10p.

Predmety: CONVOLUTIONAL neural networks, ARCHITECTURAL design, SPATIAL arrangement, MODULAR coordination (Architecture)

A survey and taxonomy of adversarial neural networks for text‐to‐image synthesis.

Autori: Agnese, Jorge Herrera, Jonathan Tao, Haicheng a ďalší

Zdroj: WIREs: Data Mining & Knowledge Discovery. Jul/Aug2020, Vol. 10 Issue 4, p1-26. 26p.

Predmety: *Artificial neural networks, *Machine translating, *Taxonomy, Convolutional neural networks, Architectural design, Deep learning

Attention module incorporated transfer learning empowered deep learning-based models for classification of phenotypically similar tropical cattle breeds (Bos indicus)

Autori: Warhade, Radhika Devi, Indu Singh, Naseeb a ďalší

Zdroj: Tropical Animal Health & Production. Jul2024, Vol. 56 Issue 6, p1-15. 15p.

A comprehensive construction of deep neural network‐based encoder–decoder framework for automatic image captioning systems.

Autori: Rahman, Md Mijanur Uzzaman, Ashik Sami, Sadia Islam a ďalší

Zdroj: IET Image Processing (Wiley-Blackwell). 12/11/2024, Vol. 18 Issue 14, p4778-4798. 21p.

Predmety: *ARTIFICIAL neural networks, CONVOLUTIONAL neural networks, DEEP learning, IMAGING systems

A Multi-Scale attention network for building extraction from high-resolution remote sensing images.

Autori: Chang J He X Song D a ďalší

Zdroj: Scientific reports [Sci Rep] 2025 Jul 10; Vol. 15 (1), pp. 24938. Date of Electronic Publication: 2025 Jul 10.

Spôsob vydávania: Journal Article

Informácie o časopise: Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: PubMed not MEDLINE; MEDLINE

Xuzhou Medical University Researchers Have Published New Study Findings on Engineering (CariesAttNet: An Attention-Enhanced Encoder-Decoder Network for Automated Caries Segmentation in CBCT Images).

Zdroj: Health & Medicine Week. 9/12/2025, p8287-8287. 1p.