Recognition recipes with deep machine learning
Автор: Ulyanov Sergey, Filipyev Andrey, Koshelev Kirill
Журнал: Сетевое научное издание «Системный анализ в науке и образовании» @journal-sanse
Статья в выпуске: 2, 2020 года.
Бесплатный доступ
This article aims to reveal that deep machine learning algorithms can be applied in a variety of commercial companies in order to improve developing intelligent systems. The major task which would be discussed in the application of convolutional neural networks for recognizing recipes of products and providing the possibility of maintenance decision making in business processes. Besides algorithms, the problems of real projects like gathering and preprocessing data would be considered and possible solutions suggested.
Deep learning, intelligence systems, convolutional neural networks, image recognition, decision making systems, artificial intelligence
Короткий адрес: https://sciup.org/14123313
IDR: 14123313
Список литературы Recognition recipes with deep machine learning
- Nemkov R. M. Development of neural network algorithms for invariant pattern recognition: dissertation of the candidate of technical sciences: 05.13.18. Stavropol. — 2015. — P. 162.
- Haykin S. Nejronnije seti: polnij kurs [Neural networks: full course]. — Moscow, 2008. — Pp. 113, 281-330.
- Gonzalez R. Tsifrovaya obrabotka izobrazhenij [Digital image processing]. — Moscow, 2012. — P. 1104.
- Ranzato M. A., Jarrett K., Kavukcuoglu K., LeCun Y. What is the best multi-stage architecture for object recognition? In ICCV, 2009.
- Richard S. Sutton. Obuchenije s podkreplenijem [Reinforcement training]. — Moscow, 2011. — P. 399.
- Ackley D. H., Hinton G. E., Sejnowski T. J. A learning algorithm for Boltzmann machines. Cognitive Science. — 1985. — Vol. 9. — Pp. 147-169.
- Bengio Y. Learning deep architectures for AI. Foundations and Trends in Machine Learning. — 2009. — Vol. 2. — Issue 1. — Pp. 1-127.
- Ciresan D., Meier U., Schmidhuber J. Multicolumn Deep Neural Networks for Image Classification [R]. In Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), CVPR '12, pp.3642-3649, Washington, DC, USA, 2012. — IEEE ComputerSociety.
- Ranzato M., Huang F., Boureau Y., LeCun Y. Unsupervised learning of invariant feature hierarchies with applications to object recognition [R]. In Proceedings of the Computer Vision and Pattern Recogni-tion Conference (CVPR’07), IEEE Press, 2007.
- Gill F. Prakticheskaya optimizatsiya [Practical optimization]. — Moscow, 1985. — P. 509.
- Izmajlov A. F. Chislennije metody optimizatsii [Numerical optimization methods]. — Moscow, 2005. — P. 304.
- Tarkhov D. A. Nejrosetevije modeli i algoritmy [Neural network models and algorithms]. — Moscow, 2014. — P. 352.
- Lemley J., Bazrafkan S., Corcoran P. Smart augmentation learning an optimal data augmentation strate-gy. — IEEE Access, 2017. — Vol. 5. — Pp. 5858-5869.
- Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. —arXiv:1409.1556.
- Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions. — arXiv:1610.02357.
- Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He Aggregated Residual Transfor-mations for Deep Neural Networks. — arXiv:1611.05431.
- Buslaev A., Parinov A., Khvedchenya E., Iglovikov V., Kalinin A. Albumentations: fast and flexible image augmentations. — arXiv:1809.06839.
