Various Deep Learning Algorithms in Computational Intelligence

This reprint highlights the importance of Deep Learning (DL), which has garnered significant attention in science, industry, and academia. It draws inspiration from the functioning of the human brain and the concept of learning. Unlike traditional and machine learning methods, deep learning techniqu...

Full description

Bibliographic Details
Format: eBook
Language:English
Published: Basel MDPI - Multidisciplinary Digital Publishing Institute 2023
Subjects:
CNN
DNS
FPN
GAN
GIS
GRU
n/a
PSO
RPN
Online Access:Open Access: DOAB: description of the publication
Open Access: DOAB, download the publication
LEADER 05447namaa2201369uu 4500
001 doab112494
003 oapen
005 20230808
006 m o d
007 cr|mn|---annan
008 230808s2023 xx |||||o ||| 0|eng d
020 |a 9783036581385 
020 |a 9783036581392 
020 |a books978-3-0365-8139-2 
024 7 |a 10.3390/books978-3-0365-8139-2  |2 doi 
040 |a oapen  |c oapen 
041 0 |a eng 
042 |a dc 
072 7 |a KNTX  |2 bicssc 
072 7 |a UY  |2 bicssc 
720 1 |a Ross, Oscar Humberto  |4 edt 
720 1 |a Ross, Oscar Humberto  |4 oth 
245 0 0 |a Various Deep Learning Algorithms in Computational Intelligence 
260 |a Basel  |b MDPI - Multidisciplinary Digital Publishing Institute  |c 2023 
300 |a 1 online resource (282 p.) 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
506 0 |a Open Access  |f Unrestricted online access  |2 star 
520 |a This reprint highlights the importance of Deep Learning (DL), which has garnered significant attention in science, industry, and academia. It draws inspiration from the functioning of the human brain and the concept of learning. Unlike traditional and machine learning methods, deep learning techniques emulate the human brain's neural networks at a lower scale, allowing them to process and analyze substantial quantities of unstructured data. The remarkable proficiency of deep learning in unveiling intricate structures within extensive datasets genuinely resembles the extraordinary aptitude of the brain to recognize patterns and form complex connections. This unique characteristic allows DL to excel in modeling and solving complex problems across various scientific and technological fields. Just as the brain learns from experience, DL architectures learn through algorithms from data by adjusting numerous parameters during training to optimize their performance and accuracy. This concept of learning and adaptation is fundamental to DL's success. This reprint serves as an excellent opportunity to disseminate current knowledge beyond academic boundaries, reaching a diverse audience encompassing academics, professionals, and the general public. This wide readership fosters the potential for meaningful connections to established projects and the cultivation of collaboration for future research endeavors. 
540 |a Creative Commons  |f https://creativecommons.org/licenses/by/4.0/  |2 cc  |u https://creativecommons.org/licenses/by/4.0/ 
546 |a English 
650 7 |a Computer science  |2 bicssc 
650 7 |a Information technology industries  |2 bicssc 
653 |a affective words 
653 |a angle detection box 
653 |a artificial neural network 
653 |a attention mechanism 
653 |a automatic optical inspection 
653 |a backpropagation neural network (BPNN) 
653 |a barrier options 
653 |a BDLSTM 
653 |a Black-Scholes model 
653 |a breast segmentation 
653 |a CNN 
653 |a CNN-LSTMs 
653 |a computer vision 
653 |a cubical complex 
653 |a cubical homology 
653 |a data analysis 
653 |a decision making 
653 |a deep learning 
653 |a DNS 
653 |a domain 
653 |a dynamic smoothing 
653 |a emotion distribution learning 
653 |a Faster-RCNN 
653 |a feature fusion 
653 |a fine-tune 
653 |a firewall 
653 |a FPN 
653 |a GAN 
653 |a generative adversarial network 
653 |a generative model 
653 |a ghettos 
653 |a GIS 
653 |a GRU 
653 |a hybrid deep learning 
653 |a image classification 
653 |a image generation 
653 |a image synthesis 
653 |a Inception score 
653 |a k-Nearest Neighbor (kNN) 
653 |a labor exports 
653 |a LSTM 
653 |a machine learning 
653 |a malicious 
653 |a mammogram 
653 |a MobileNetV3 
653 |a modeling 
653 |a multi-task CNN 
653 |a n/a 
653 |a name 
653 |a networks 
653 |a Northeast Asian Countries 
653 |a object detection 
653 |a optimization of convolutional neural networks 
653 |a option Greeks 
653 |a persistent homology 
653 |a polynomial regression 
653 |a precipitation nowcasting 
653 |a PredRNN_v2 
653 |a PSO 
653 |a radar image prediction 
653 |a rain radar 
653 |a random forest regression 
653 |a random forest regression (RFR) 
653 |a RPN 
653 |a SARS-CoV-2 
653 |a scoreGAN 
653 |a segregation 
653 |a semantic segmentation 
653 |a sign language recognition 
653 |a ski goggles lenses 
653 |a Stacked LSTM 
653 |a surface defect 
653 |a text-based emotion analysis 
653 |a time series 
653 |a traffic sign detection 
653 |a UNet 
653 |a Washington D.C. 
653 |a waste classification 
653 |a YOLOv5 
653 |a you only look once (YOLO) 
793 0 |a DOAB Library. 
856 4 0 |u https://directory.doabooks.org/handle/20.500.12854/112494  |7 0  |z Open Access: DOAB: description of the publication 
856 4 0 |u https://mdpi.com/books/pdfview/book/7610  |7 0  |z Open Access: DOAB, download the publication