Convolutional Neural Network Layers and Architectures
Convolutional Neural Network Layers and Architectures
Autori:
Izdanje: International Scientific Conference on Information Technology and Data Related Research
DOI: 10.15308/Sinteza-2019-445-451
Oblast: Data Science & Digital Broadcasting Systems
Stranice: 445-451
Apstrakt:
In recent years, computer vision which is one of the fastest growing artificial intelligence disciplines, has become increasingly important in our society due to its wide range applications in different areas such as health care and medicine (algorithms that can diagnose medical images for diseases), vision- based robotics, self-driving cars (that can see and drive safely). Convolutional neural networks are biologically inspired architectures and represent the core of deep learning algorithms in computer vision. In this paper, we represent the fundamental building blocks of convolutional neural networks and the most popular convolutional neural network architectures in the history, including those that have achieved the state-of-the-art performance on standard recognition datasets and tasks such as ImageNet Large-Scale Visual Recognition Challenge (ILSVRC). ILSVRC is one of the largest challenges in computer vision organized by Stanford Vision Lab since 2010 and every year teams compete to claim the state-of-the-art performance on the dataset.
Ključne reči: computer vision, deep learning, image recognition, image classification, object recognition
Priložene datoteke:
- 445-451 ( veličina: 897,11 KB, broj pregleda: 482 )
Zahvaljujemo se što ste preuzeli publikaciju sa portala Singipedia.
Ukoliko želite da se prijavite za obaveštenja o sadržajima iz oblasti ove publikacije, možete nam ostaviti adresu svoje elektronske pošte.
Preuzimanje citata:
BibTeX format
RefWorks Tagged format
Unapred formatirani prikaz citata
BibTeX format
@article{article, author = {T. Bezdan and N. Bačanin Džakula}, title = {Convolutional Neural Network Layers and Architectures}, journal = {International Scientific Conference on Information Technology and Data Related Research}, year = 2020, pages = {445-451}, doi = {10.15308/Sinteza-2019-445-451} }
RT Conference Proceedings A1 Timea Bezdan A1 Nebojša Bačanin Džakula T1 Convolutional Neural Network Layers and Architectures AD Univerzitet Singidunum, Beograd, Beograd, Srbija YR 2020 NO doi: 10.15308/Sinteza-2019-445-451
T. Bezdan and N. Bačanin Džakula, Convolutional Neural Network Layers and Architectures, Univerzitet Singidunum, Beograd, 2020, doi:10.15308/Sinteza-2019-445-451