Suchergebnisse - "Recurrent autoencoder model"

Unveiling complex brain dynamics during movie viewing via deep recurrent autoencoder model

Autoren: Kexin Wang Limei Song Zhaowei Li et al.

Quelle: NeuroImage, Vol 310, Iss , Pp 121177- (2025)

Schlagwörter: Naturalistic fMRI, Recurrent autoencoder model, Sliding window strategy, Movie narrative structure, Dynamic large-scale brain networks, Neurosciences. Biological psychiatry. Neuropsychiatry, RC321-571

Dateibeschreibung: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S105381192500179X; https://doaj.org/toc/1095-9572

Zugangs-URL: https://doaj.org/article/762804abd39343e7bf399d203877e5a9

Recurrent autoencoder model for unsupervised seismic facies analysis

Autoren: Yanhui Zhou Wenchao Chen

Quelle: Interpretation. 10:T451-T460

Schlagwörter: 01 natural sciences, 0105 earth and related environmental sciences

A topic-enhanced recurrent autoencoder model for sentiment analysis of short texts

Autoren: Guobing Zou Ming Gao Shaochun Wu et al.

Quelle: International Journal of Internet Manufacturing and Services. 7:393

Zugangs-URL: https://www.inderscienceonline.com/doi/abs/10.1504/IJIMS.2020.110230

Prediction of reverberation intensity based on convolutional cyclic self-coding model.

Autoren: Chen, Changkai Gao, Bo Li, Gongyun et al.

Quelle: Journal of Physics: Conference Series; 2025, Vol. 3007 Issue 1, p1-7, 7p

AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements

Autoren: Yeung, Calvin Ide, Kenjiro Fujii, Keisuke

Index Begriffe: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, text

URL: http://arxiv.org/abs/2405.12070

Identification of Environmental Noise Traces in Seismic Recordings Using Vision Transformer and Mel-Spectrogram.

Autoren: Ding, Qianlong Chen, Shuangquan Shen, Jinsong et al.

Quelle: Applied Sciences (2076-3417); Aug2025, Vol. 15 Issue 15, p8586, 18p

Schlagwörter: DATA quality, QUALITY control, TIME-frequency analysis, NOISE pollution, SIGNAL denoising, SEISMIC surveys, SIGNAL classification, TRANSFORMER models

Application of BERT-GCN Model Based on Strong Link Relation Graph in Water Use Enterprise Classification.

Autoren: Xiang, Junhong Zheng, Baoxian Cai, Chenkai et al.

Quelle: Applied Sciences (2076-3417); May2025, Vol. 15 Issue 9, p4681, 16p

Schlagwörter: LANGUAGE models, FEATURE extraction, WATER currents, WATER quality, WATER use

Wireless mmWave Communication in 5G Network Slicing With Routing Model Based on IoT and Deep Learning Model

Autoren: R. Suganya L. R. Sujithra Ramesh Kumar Ayyasamy et al.

Quelle: Transactions on Emerging Telecommunications Technologies. 36

Addressing posterior collapse by splitting decoders in variational recurrent autoencoders.

Autoren: Sun, Jianyong Song, Fan Li, Qiaohong

Quelle: Neurocomputing. Feb2024, Vol. 570, pN.PAG-N.PAG. 1p.

Schlagwörter: *NATURAL language processing, *RECURRENT neural networks, *LATENT variables, *RANDOM variables, *DECODING algorithms, *HUMAN fingerprints

Anomaly detection in surveillance videos: a thematic taxonomy of deep models, review and performance analysis.

Autoren: Chandrakala, S. Deepak, K. Revathy, G.

Quelle: Artificial Intelligence Review; Apr2023, Vol. 56 Issue 4, p3319-3368, 50p

Schlagwörter: VIDEO surveillance, ANOMALY detection (Computer security), GENERATIVE adversarial networks, VISUAL fields, DEEP learning, TAXONOMY

Predicting waves in fluids with deep neural network.

Autoren: Deo, Indu Kant Jaiman, Rajeev

Quelle: Physics of Fluids; Jun2022, Vol. 34 Issue 6, p1-22, 22p

Schlagwörter: ARTIFICIAL neural networks, RECURRENT neural networks, WAVES (Fluid mechanics), THEORY of wave motion, DEEP learning, BURGERS' equation

Residual Spatiotemporal Autoencoder with Skip Connected and Memory Guided Network for Detecting Video Anomalies.

Autoren: Chandrakala, S. Srinivas, V. Deepak, K.

Quelle: Neural Processing Letters; Dec2021, Vol. 53 Issue 6, p4677-4692, 16p

Schlagwörter: ANOMALY detection (Computer security), STREAMING video & television, MEMORY, VIDEOS, MEMORIZATION

Assessment of unsteady flow predictions using hybrid deep learning based reduced-order models.

Autoren: Bukka, Sandeep Reddy Gupta, Rachit Magee, Allan Ross et al.

Quelle: Physics of Fluids; Jan2021, Vol. 33 Issue 1, p1-43, 43p

Schlagwörter: REDUCED-order models, BLENDED learning, DEEP learning, RECURRENT neural networks, PROPER orthogonal decomposition, UNSTEADY flow

INDRA: Intrusion Detection Using Recurrent Autoencoders in Automotive Embedded Systems.

Autoren: Kukkala, Vipin Kumar Thiruloga, Sooryaa Vignesh Pasricha, Sudeep

Quelle: IEEE Transactions on Computer-Aided Design of Integrated Circuits & Systems; Nov2020, Vol. 39 Issue 11, p3698-3710, 13p

Schlagwörter: RECURRENT neural networks, ARTIFICIAL neural networks, BUSES

Learning Normal Patterns via Adversarial Attention-Based Autoencoder for Abnormal Event Detection in Videos.

Autoren: Song, Hao Sun, Che Wu, Xinxiao et al.

Quelle: IEEE Transactions on Multimedia; Aug2020, Vol. 22 Issue 8, p2138-2148, 11p

Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels

Autoren: Lea Frermann György Szarvas

Quelle: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. :1873-1883

Schlagwörter: 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, 01 natural sciences, 0105 earth and related environmental sciences

Zugangs-URL: https://www.aclweb.org/anthology/D17-1200.pdf
https://www.aclweb.org/anthology/D17-1200.pdf
https://core.ac.uk/display/157855720
https://aclanthology.org/D17-1200/
https://dblp.uni-trier.de/db/conf/emnlp/emnlp2017.html#FrermannS17
https://findanexpert.unimelb.edu.au/scholarlywork/1403261-inducing-semantic-micro-clusters-from-deep-multi-view-representations-of-novels

Deep Convolutional Recurrent Autoencoders for Flow Field Prediction

Autoren: Sandeep Reddy Bukka Rajeev K. Jaiman Allan Ross Magee

Quelle: Volume 8: CFD and FSI.

Schlagwörter: 0103 physical sciences, Fluid Dynamics (physics.flu-dyn), FOS: Physical sciences, Physics - Fluid Dynamics, Computational Physics (physics.comp-ph), 0101 mathematics, Physics - Computational Physics, 01 natural sciences

Zugangs-URL: http://arxiv.org/pdf/2003.12147
http://arxiv.org/abs/2003.12147
https://appliedmechanicsreviews.asmedigitalcollection.asme.org/OMAE/proceedings/OMAE2020/84409/V008T08A005/1092921
https://gasturbinespower.asmedigitalcollection.asme.org/OMAE/proceedings/OMAE2020/84409/V008T08A005/1092921
https://nanoengineeringmedical.asmedigitalcollection.asme.org/OMAE/proceedings/OMAE2020/84409/V008T08A005/1092921
https://asmedigitalcollection.asme.org/OMAE/proceedings/OMAE2020/84409/V008T08A005/1092921

NervanaSystems/neon: Faster RCNN, Sequence to Sequence, Reshape layer, updated pip requirements

Autoren: Scott Leishman apark263 Anil Thomas et al.

Relation: https://github.com/NervanaSystems/neon/tree/v1.6.0; https://zenodo.org/records/154612; oai:zenodo.org:154612; https://doi.org/10.5281/zenodo.154612

Verfügbarkeit: https://doi.org/10.5281/zenodo.154612
https://zenodo.org/records/154612

Computational Science €“ ICCS 2023

Autoren: Jiří Mikyška Clélia de Mulatier Maciej Paszynski et al.

Resource Type: eBook.

Schlagworte: Computer science, Artificial intelligence, Computer engineering, Computer networks, Software engineering, Computer science—Mathematics

Categories: COMPUTERS / Computer Science, COMPUTERS / Artificial Intelligence / General, COMPUTERS / Software Development & Engineering / General, COMPUTERS / Hardware / General, MATHEMATICS / Applied

Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing : Use Cases and Emerging Challenges

Autoren: Sudeep Pasricha Muhammad Shafique

Resource Type: eBook.

Schlagworte: Embedded computer systems, Electronic circuits, Cooperating objects (Computer systems)

Categories: COMPUTERS / Embedded Computer Systems, COMPUTERS / Cybernetics, TECHNOLOGY & ENGINEERING / Electronics / General, TECHNOLOGY & ENGINEERING / Electronics / Circuits / General