Suchergebnisse - "backpropagation algorithms"

A THEORETICAL INVESTIGATION ON TRAINING OF PIPE-LIKE NEURAL NETWORK BENCHMARK ARCHITECTURES AND PERFORMANCE COMPARISONS OF POPULAR TRAINING ALGORITHMS

Autoren: Özlem İMİK ŞİMŞEK Barış Baykant ALAGÖZ

Quelle: Volume: 10, Issue: 4 1251-1271
Mühendislik Bilimleri ve Tasarım Dergisi
Journal of Engineering Sciences and Design

Schlagwörter: Computer Software, 0301 basic medicine, 03 medical and health sciences, Yapay Sinir Ağları, Ağ Mimarileri, Eğitim Performansı, Geriyeyayılım Algoritmaları, Metasezgisel Eğitim, Artificial Neural Networks, Network Architectures, Training Performance, Backpropagation Algorithms, Metaheuristic Training, 0211 other engineering and technologies, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, Bilgisayar Yazılımı

Dateibeschreibung: application/pdf

Zugangs-URL: https://dergipark.org.tr/tr/pub/jesd/issue/74419/1104772

Optimization of the Activation Function for Predicting Inflation Levels to Increase Accuracy Values

Autoren: Windarto, Agus Perdana Rahadjeng, Indra Riyana Siregar, Muhammad Noor Hasan et al.

Quelle: JURNAL MEDIA INFORMATIKA BUDIDARMA; Vol 8, No 3 (2024): Juli 2024; 1627-1636 ; 2548-8368 ; 2614-5278 ; 10.30865/mib.v8i3

Schlagwörter: Backpropagation Algorithms, Artificial Neural Networks, Inflation Prediction, Economic Planning

Dateibeschreibung: application/pdf

Relation: https://ejurnal.stmik-budidarma.ac.id/mib/article/view/7776/3930

Verfügbarkeit: https://ejurnal.stmik-budidarma.ac.id/mib/article/view/7776
https://doi.org/10.30865/mib.v8i3.7776

Automatic Polyp Detection Using Microwave Endoscopy for Colorectal Cancer Prevention and Early Detection: Phantom Validation

Autoren: Alejandra Garrido Roberto Sont Walid Dghoughi et al.

Weitere Verfasser: Alejandra Garrido Roberto Sont Walid Dghoughi et al.

Quelle: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
IEEE Access, Vol 9, Pp 148048-148059 (2021)

Schlagwörter: Endoscopes, Backpropagation algorithms, microwave antenna arrays, Medical diagnostic imaging, Colonoscòpia, medical diagnostic imaging, Colonoscopy, 02 engineering and technology, Microwave devices, Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal, Enginyeria de la telecomunicació::Processament del senyal [Àrees temàtiques de la UPC], TK1-9971, 3. Good health, Dispositius de microones, Diagnòstic per la imatge, 03 medical and health sciences, 0302 clinical medicine, Microwave imaging, endoscopes, Microwave antenna arrays, 0202 electrical engineering, electronic engineering, information engineering, Diagnostic imaging, microwave imaging, Electrical engineering. Electronics. Nuclear engineering

Dateibeschreibung: application/pdf

Zugangs-URL: https://ieeexplore.ieee.org/ielx7/6287639/6514899/09592774.pdf
https://doaj.org/article/1d1a4e1d2f8441a4aca3b9d80afbe0cc
https://dblp.uni-trier.de/db/journals/access/access9.html#GarridoSDMRFBG21
https://upcommons.upc.edu/handle/2117/357614
https://hdl.handle.net/2117/357614
https://doi.org/10.1109/access.2021.3124019

Enhancing Deep Neural Network Saliency Visualizations With Gradual Extrapolation

Autoren: Tomasz Szandala

Quelle: IEEE Access, Vol 9, Pp 95155-95161 (2021)

Schlagwörter: FOS: Computer and information sciences, explainable artificial intelligence, Computer Science - Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Computer Science - Neural and Evolutionary Computing, 02 engineering and technology, computer vision, TK1-9971, Artificial Intelligence (cs.AI), XAI, Deep neural networks, 0202 electrical engineering, electronic engineering, information engineering, Electrical engineering. Electronics. Nuclear engineering, Neural and Evolutionary Computing (cs.NE), backpropagation algorithms, visualization

Zugangs-URL: https://ieeexplore.ieee.org/ielx7/6287639/6514899/09468713.pdf
http://arxiv.org/abs/2104.04945
https://doaj.org/article/2de5916b7f3049e4a90432f498cc0803
https://arxiv.org/pdf/2104.04945.pdf
https://dblp.uni-trier.de/db/journals/access/access9.html#Szandala21
https://ui.adsabs.harvard.edu/abs/2021arXiv210404945S/abstract
https://arxiv.org/abs/2104.04945

A Digital Signage Audience Classification Model Based on the Huff Model and Backpropagation Neural Network

Autoren: Xun Zhang Xiaolan Xie Yuxue Wang et al.

Quelle: IEEE Access, Vol 8, Pp 71708-71720 (2020)

Schlagwörter: geographic information systems, classification algorithms, 11. Sustainability, Digital signage, 0202 electrical engineering, electronic engineering, information engineering, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, backpropagation algorithms, TK1-9971

Zugangs-URL: https://ieeexplore.ieee.org/ielx7/6287639/8948470/09064779.pdf
https://doaj.org/article/774ba464283b4701a1f6fafde38caf8a

Differential convolutional neural network

Autoren: Sarıgül M. Ozyildirim B.M. Avci M. et al.

Weitere Verfasser: Sarıgül M. Ozyildirim B.M. Avci M. et al.

Quelle: Neural Networks. 116:279-287

Schlagwörter: Artificial neural network, Classification performance, Image classification, Performance, Neighborhood activation error, Data analysis, Mathematical parameters, 02 engineering and technology, Procedures, Pattern Recognition, Automated, Convolution techniques, 03 medical and health sciences, Deep Learning, 0302 clinical medicine, Statistical tests, Artificial Intelligence, Pattern recognition, Convolutional model, Machine learning, Its efficiencies, 0202 electrical engineering, electronic engineering, information engineering, Humans, Error back propagation algorithm, Adaptation, Improved back propagation algorithm, Priority journal, Backpropagation algorithms, Learning systems, Intermethod comparison, Measurement accuracy, Neurosciences, Deep learning, Neural Networks (Computer), Chemical activation, Classification, Back propagation, Automated pattern recognition, Convolution, Algorithm, Analytical error, Computer Science, Experiment sets, Convolutional neural networks, Neural Networks, Computer, Trends, Controlled study, Neural networks, Human

Dateibeschreibung: application/pdf

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/31125914
https://dblp.uni-trier.de/db/journals/nn/nn116.html#SarigulOA19
https://europepmc.org/article/MED/31125914
https://doi.org/10.1016/j.neunet.2019.04.025
https://www.sciencedirect.com/science/article/abs/pii/S0893608019301315
https://www.ncbi.nlm.nih.gov/pubmed/31125914
https://pubmed.ncbi.nlm.nih.gov/31125914/
https://hdl.handle.net/20.500.12508/543

Time Series Forecasting Using Neural Networks: Are Recurrent Connections Necessary?

Autoren: Salihu A. Abdulkarim Andries P. Engelbrecht

Quelle: Neural Processing Letters. 50:2763-2795

Schlagwörter: Artificial neural network (ANN), Time series, Resilient propagation, Backpropagation algorithms, Classical back-propagation, 02 engineering and technology, Neural network, Recurrent neural networks, Modeling and forecasting, Particle swarm optimization (PSO), Time series forecasting, 0202 electrical engineering, electronic engineering, information engineering, Cooperative quantum particle swarm optimization, Dynamic optimization problem (DOP), Dynamic environments, Quantum particle swarm optimization, Non-stationary environment, Forecasting

Dateibeschreibung: application/pdf

Zugangs-URL: https://repository.up.ac.za/handle/2263/70762
https://doi.org/10.1007/s11063-019-10061-5
https://link.springer.com/article/10.1007/s11063-019-10061-5
https://dblp.uni-trier.de/db/journals/npl/npl50.html#AbdulkarimE19

Comparison of Hospital Building’s Energy Consumption Prediction Using Artificial Neural Networks, ANFIS, and LSTM Network

Autoren: Dimitrios K. Panagiotou Anastasios I. Dounis

Quelle: Energies, Vol 15, Iss 6453, p 6453 (2022)

Schlagwörter: artificial neural networks, adaptive neuro-fuzzy adaptive inference system, long short-term memory networks, backpropagation algorithms, metaheuristic algorithms, machine learning, Technology

Relation: https://www.mdpi.com/1996-1073/15/17/6453; https://doaj.org/toc/1996-1073; https://doaj.org/article/64830c94f5a444809655a8efb364a698

Verfügbarkeit: https://doi.org/10.3390/en15176453
https://doaj.org/article/64830c94f5a444809655a8efb364a698

Multilayer Perceptron: An Intelligent Model for Classification and Intrusion Detection

Autoren: Amato Flora Mazzocca Nicola VIVENZIO, EMILIO et al.

Quelle: 2017 31st International Conference on Advanced Information Networking and Applications Workshops (WAINA). :686-691

Schlagwörter: Intelligent modeling, Intrusion detection, Machine learning, Multilayer perceptron, Network security, Neural networks, Computer Networks and Communications, Hardware and Architecture, Information Systems, Safety, Risk, Reliability and Quality, Information Systems and Management, Backpropagation algorithms, Classification (of information), Learning systems, Mercury (metal), Multilayer neural networks, 02 engineering and technology, Public dataset, Sigmoidal activation functions, Common interests, Multilayers, 0202 electrical engineering, electronic engineering, information engineering, Safety, Risk, Reliability and Quality, Neural networks, Common interests, Computer device, Multi layer perceptron, Performance of systems, Training epochs, Network security, Training epochs

Dateibeschreibung: application/pdf

Zugangs-URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85021407627&doi=10.1109/WAINA.2017.134&partnerID=40&md5=f955d13dc3a325e734009328247e4e80
http://hdl.handle.net/11588/715146
http://ieeexplore.ieee.org/document/7929765/
https://ieeexplore.ieee.org/document/7929765/
https://doi.org/10.1109/WAINA.2017.134
https://dblp.uni-trier.de/db/conf/aina/ainaw2017.html#AmatoMMV17
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85021407627&doi=10.1109/WAINA.2017.134&partnerID=40&md5=f955d13dc3a325e734009328247e4e80
https://hdl.handle.net/11588/715146
https://doi.org/10.1109/WAINA.2017.134
https://hdl.handle.net/11591/383037
https://doi.org/10.1109/WAINA.2017.134

Prediction of main particulars of a chemical tanker at preliminary ship design using artificial neural network

Autoren: Samet Gurgen Ismail Altin Murat Ozkok et al.

Weitere Verfasser: Samet Gurgen Ismail Altin Murat Ozkok et al.

Quelle: Ships and Offshore Structures. 13:459-465

Schlagwörter: Artificial neural network, Container Ship | Whipping | Slamming, Preliminary ship design, Marine, Backpropagation algorithms, Shipbuilding, Backpropagation learning algorithm, Chemical tankers, Backpropagation, 02 engineering and technology, 16. Peace & justice, Chemical tanker, Preliminary ship designs, 0201 civil engineering, Artificial neural network models, Engineering, Correlation coefficient, Tankers (ships), Mean absolute percentage error, Sailing vessels, High-accuracy, Neural networks, Ships

Dateibeschreibung: application/pdf

Zugangs-URL: https://avesis.ktu.edu.tr/yayin/79ff0899-5cf7-4e8a-8336-4db93729a05d/prediction-of-main-particulars-of-a-chemical-tanker-at-preliminary-ship-design-using-artificial-neural-network
https://trid.trb.org/view/1506561
https://www.tandfonline.com/doi/full/10.1080/17445302.2018.1425337
https://hdl.handle.net/20.500.12508/726

Improved Lower Bounds on Mutual Information Accounting for Nonlinear Signal--Noise Interaction

Autoren: Irukulapati, Maga Secondini, Marco Agrell, Erik et al.

Quelle: Journal of Lightwave Technology. 36(22):5152-5159

Schlagwörter: Achievable information rate, auxiliary channel, fiber-optical communications, mismatched decoding, nonlinear compensation, stochastic digital backpropagation, Backpropagation algorithms, Fiber optics, Nonlinear optics, Signal noise measurement, Stochastic systems, Digital backpropagation, Fiber optical communications, Non-linear compensations, Optical fiber communication

Dateibeschreibung: print

Zugangs-URL: https://urn.kb.se/resolve?urn=urn:nbn:se:ri:diva-35200

CREDIT RISK PREDICTION USING NEURAL NETWORK BACKPROPAGATION ALGORITHM

Autoren: Maradu Sihombing Erwin D. Sitanggang

Quelle: INFOKUM; Vol. 10 No. 1 (2021): Desember, Data Mining, Image Processing, and artificial intelligence; 1-10 ; 2722-4635 ; 2302-9706

Schlagwörter: Predictions, credit risk, Neural Networks, Backpropagation Algorithms

Dateibeschreibung: application/pdf

Relation: https://infor.seaninstitute.org/index.php/infokum/article/view/2903/2598; https://infor.seaninstitute.org/index.php/infokum/article/view/2903

Verfügbarkeit: https://infor.seaninstitute.org/index.php/infokum/article/view/2903

Credit risk prediction using neural network backpropagation algorithm

Autoren: Sihombing, Maradu Sitanggang, Erwin D Maranata Pasaribu et al.

Quelle: INFOKUM; Vol. 10 No. 1 (2021): Desember, Data Mining, Image Processing, and artificial intelligence; 1-10 ; 2722-4635 ; 2302-9706

Schlagwörter: Predictions, credit risk, Neural Networks, Backpropagation Algorithms

Dateibeschreibung: application/pdf

Relation: https://infor.seaninstitute.org/index.php/infokum/article/view/196/152; https://infor.seaninstitute.org/index.php/infokum/article/view/196

Verfügbarkeit: https://infor.seaninstitute.org/index.php/infokum/article/view/196

Basin scale wind-wave prediction using empirical orthogonal function analysis and neural network models

Autoren: Mrinmoyee Bhattacharya Mourani Sinha

Quelle: Results in Geophysical Sciences, Vol 8, Iss , Pp 100032- (2021)

Schlagwörter: Empirical orthogonal function analysis, Neural network models, Backpropagation algorithms, Significant wave height, Bay of Bengal, Geophysics. Cosmic physics, QC801-809, Geology, QE1-996.5

Relation: http://www.sciencedirect.com/science/article/pii/S2666828921000237; https://doaj.org/toc/2666-8289; https://doaj.org/article/1ffa929ba2784f24bfc121630baaf95c

Verfügbarkeit: https://doi.org/10.1016/j.ringps.2021.100032
https://doaj.org/article/1ffa929ba2784f24bfc121630baaf95c

Artificial Neural Networks for Prediction of Steadman Heat Index

Autoren: Chand, Bhuwan Nguyen-Huy, Thong Deo, Ravinesh C.

Quelle: Springer Transactions in Civil and Environmental Engineering ISBN: 9789811557712

Schlagwörter: 13. Climate action, heatwaves prediction, hidden transfer, 4. Education, 11. Sustainability, data-driven, artificial neural networks, backpropagation algorithms

Zugangs-URL: https://eprints.usq.edu.au/39217/
http://eprints.usq.edu.au/39217/
https://link.springer.com/chapter/10.1007%2F978-981-15-5772-9_16

3D FEATURE POINT EXTRACTION FROM LIDAR DATA USING A NEURAL NETWORK

Autoren: Yu Feng Claus Brenner Alexander Schlichting

Quelle: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLI-B1, Pp 563-569 (2016)

Schlagwörter: Technology, Feature points extraction, LiDAR, Corner detector, Backpropagation, Extraction, 02 engineering and technology, 03 medical and health sciences, 0302 clinical medicine, Mobile mapping system, 11. Sustainability, 0202 electrical engineering, electronic engineering, information engineering, Applied optics. Photonics, Edge detection, Konferenzschrift, Dewey Decimal Classification::500 | Naturwissenschaften, Backpropagation algorithms, Image matching, Vehicles, 3D feature points extraction, Remote sensing, Engineering (General). Civil engineering (General), Neural network, Dewey Decimal Classification::500 | Naturwissenschaften::520 | Astronomie, Kartographie, TA1501-1820, Autonomous driving, Lidar point clouds, TA1-2040, Poles, Feature point extraction, Neural networks

Dateibeschreibung: application/pdf

Zugangs-URL: https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B1/563/2016/isprs-archives-XLI-B1-563-2016.pdf
https://isprs-archives.copernicus.org/articles/XLI-B1/563/2016/
https://doaj.org/article/4e77b477c5ad4065be0710076709a008
http://ui.adsabs.harvard.edu/abs/2016ISPAr41B1..563F/abstract
https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B1/563/2016/
https://noa.gwlb.de/receive/cop_mods_00013134
https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B1/563/2016/isprs-archives-XLI-B1-563-2016.pdf
https://www.repo.uni-hannover.de/handle/123456789/714

An Optimized Artificial Neural Network Structure to Predict Clay Sensitivity in a High Landslide Prone Area Using Piezocone Penetration Test (CPTu) Data: A Case Study in Southwest of Sweden

Autoren: Abbaszadeh Shahri, Abbas

Quelle: Geotechnical and Geological Engineering. :1-14

Schlagwörter: Artificial neural network model, Clay sensitivity, Landslide, Piezocone penetration test, Backpropagation, Backpropagation algorithms, Forecasting, Geotechnical engineering, Landslides, Neural networks, Optimization, Regression analysis, Soil testing, Artificial neural network modeling, Conjugate gradient descents, Feed-forward back-propagation neural networks, Laboratory investigations, Landslide-prone areas, Piezocone penetration tests, Site characterization, Sensitivity analysis

Dateibeschreibung: print

Zugangs-URL: https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-188334

Neural networks as on-line approximators of nonlinear systems

Autoren: Polycarpou, Marios M. Ioannou, P. A. Polycarpou, Marios M. [0000-0001-6495-9171]

Weitere Verfasser: Polycarpou, Marios M. Ioannou, P. A. Polycarpou, Marios M. [0000-0001-6495-9171]

Quelle: 1992] Proceedings of the 31st IEEE Conference on Decision and Control

Schlagwörter: Identification, 0209 industrial biotechnology, Feedforward neural networks, Artificial neural networks, Backpropagation algorithms, Linearly parametrized networks, Modeling, Neural nets, Approximation theory, Ear, 02 engineering and technology, Approximation methods, Neural network, Power system modeling, Discrete-time formulation, Mathematical model, Online approximation, Discrete-time dynamical systems, Nonlinear systems, 0202 electrical engineering, electronic engineering, information engineering, Nonlinear dynamical systems, Stability, Neural networks, Upper bound, Nonlinearly parametrized networks

Zugangs-URL: http://ieeexplore.ieee.org/document/371802/
https://ieeexplore.ieee.org/document/371802/
http://gnosis.library.ucy.ac.cy/handle/7/44670

Artificial Neural Network Modeling and Simulation of In-VitroNanoparticle-Cell Interactions

Autoren: Cenk, N. Budak G. Dayanik, S. et al.

Weitere Verfasser: Cenk, N. Budak G. Dayanik, S. et al.

Quelle: Journal of Computational and Theoretical Nanoscience

Schlagwörter: Medical nanotechnology, Optimization, Polymethyl methacrylates, 0301 basic medicine, Nanoparticle Uptake Rate, Advanced technology, 03 medical and health sciences, Prediction model, Feedforward backpropagation, Artificial Neural Networks, Targeted drug delivery, Mathematical models, 0303 health sciences, Backpropagation algorithms, Cellular uptake efficiency, Targeted Drug Delivery, Nanoparticle uptakes, Computer simulation, Prediction Model, Artificial neural network modeling, 3. Good health, Cell membranes, Nanomedicine, Drug delivery, Dispersion characteristics, Nanoparticles, Experiments, Cytology, Neural networks

Dateibeschreibung: application/pdf

Zugangs-URL: http://repository.bilkent.edu.tr/bitstream/11693/26378/1/Artificial_neural_network_modeling_and_simulation_of_in-vitro_nanoparticle-cell_interactions.pdf
https://ui.adsabs.harvard.edu/abs/2014JCTN...11..272C/abstract
https://hdl.handle.net/20.500.12573/182
https://hdl.handle.net/11693/26378

A neural-based architecture for spot-noisy logo recognition

Autoren: F. Cesarini E. Francesconi M. Gori et al.

Quelle: Proceedings of the Fourth International Conference on Document Analysis and Recognition. 1:175-179

Schlagwörter: Noise robustness, Neural networks, Backpropagation algorithms, Image recognition, Artificial neural networks, Trademarks, Logo, Noise generators, Autoencoder, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology

Zugangs-URL: https://hdl.handle.net/2158/597409
https://doi.org/10.1109/ICDAR.1997.619836