Image Classification Using Reinforcement Learning
Main Article Content
Abstract
Recently, such a direction of machine learning as reinforcement learning has been actively developing. As a consequence, attempts are being made to use reinforcement learning for solving computer vision problems, in particular for solving the problem of image classification. The tasks of computer vision are currently one of the most urgent tasks of artificial intelligence.
The article proposes a method for image classification in the form of a deep neural network using reinforcement learning. The idea of the developed method comes down to solving the problem of a contextual multi-armed bandit using various strategies for achieving a compromise between exploitation and research and reinforcement learning algorithms. Strategies such as -greedy, -softmax, -decay-softmax, and the UCB1 method, and reinforcement learning algorithms such as DQN, REINFORCE, and A2C are considered. The analysis of the influence of various parameters on the efficiency of the method is carried out, and options for further development of the method are proposed.
Article Details
References
2. Krizhevsky A., Sutskever I., Hinton G. E. ImageNet Classification with Deep Convolutional Neural Networks // Advances in neural information processing systems, 2012. Vol. 25, No. 2. P. 1097–1105, DOI: 10.1145/3065386.
3. Russakovsky O., Deng J., Su H. at all. ImageNet Large Scale Visual Recog-nition Challenge // International Journal of Computer Vision. 2015. Vol. 115, No. 3. P. 211–252, DOI: 10.1007/s11263-015-0816-y.
4. Sutton R. S., Barto A. G. Reinforcement learning: An introduction // C.: The MIT Press, 2018. URL: http://www.incompleteideas.net/book/RLbook2020.pdf/.
5. Liu X., Xia T., Wang J. at all. Fully Convolutional Attention Networks for Fine-Grained Recognition // arXiv:1603.06765, 2017.
6. Li Z., Yang Y., Liu X. at all. Dynamic Computational Time for Visual Atten-tion // arXiv:1703.10332, 2017.
7. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recogni-tion // Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016. P. 770–778, DOI: 10.1109/CVPR.2016.90.
8. PyTorch, 2016, URL: https://pytorch.org/.
9. Google Colaboratory, 2017, URL: https://colab.research.google.com/.
10. ImageNet Dataset, 2016, URL: http://image-net.org/.
11. Fine-Grained Image Classification, 2019, URL: https://paperswithcode.com/task/fine-grained-image-classification/.
12. Girshick R. Fast R-CNN // Proceedings of the IEEE International Confer-ence on Computer Vision, 2015. P. 1440–1448, DOI: 10.1109/ICCV.2015.169.
13. Mnih V., Kavukcuoglu K., Silver D. at all. Playing Atari with Deep Rein-forcement Learning // arXiv:1312.5602, 2013.
14. Abdolmaleki A., Springenberg J. T., Degrave J. at all. Relative Entropy Regularized Policy Iteration // arXiv:1812.02256, 2018.
15. Auer P., Cesa-Bianchi N., Fischer P. Finite-time Analysis of the Multiarmed Bandit Problem // Machine Learning, 2002. Vol. 47, No. 2-3. P. 235–256, DOI: 10.1023/A:1013689704352.
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.