UDC 519.816(045)
DECOMPOSITION METHOD OF CALCULATING THE WEIGHT COEFFITIENS
OF A BINARY NEURAL NETWORK
Abstract. A method for determining the weights of a binary neural network based on its decomposition into elementary modules is presented. The approach allows tuning the weight coefficients of all the network connections at the stage of its design, which has eliminated the need to implement time-consuming iterative algorithms for learning the network during its operation. An algorithm and an example of calculating the weights are given.
Keywords: binary neural network, weights, method of determination, decomposition, algorithm.
FULL TEXT
REFERENCES
- Luger J.F. Artificial intelligence: strategies and methods for solving complex problems [Russian translation]. Moscow: Williams, 2005. 864 p.
- Russell S., Norvig P. Artificial intelligence: a modern approach [Russian translation]. Moscow: Williams, 2006. 1408 p.
- Khaikin S. Neural networks: a complete course [Russian translation]. Moscow: Williams, 2006. 1104 с.
- Callan R. Basic concepts of neural networks [Russian translation]. Moscow: Williams, 2001. 288 p.
- Shigeru O., Marzuki H., Rubia Y. Neurofeedback and its applications [Russian translation]. Moscow: IPRZHR, 2000. 272 p.
- Goodfellow J., Bengio I., Courville A. Deep learning [Russian translation]. Moscow: DMK-Press, 2017. 652 p.
- Hastie T., Tibshirani R., Friedman J. The elements of statistical learning: Data mining, inference and prediction. Springer-Verlag, 2009. 746 p.
- Opanasenko V.N., Kryvyi S.L. Synthesis of neural networks based on transformations of cyclic Hamming codes. Kibernetika i sistemnyj analiz. 2017. Vol. 53, N 4. P. 155–164.
- Palagin A.V., Opanasenko V.N., Kryvyi S.L. FPGA-based hardware implementation of cyclic Hamming code transformations. Proceedings of the 15th All-Russian scientific and technical conference "Neuroinformatics-2013". Part 3. Moscow, 2013. P. 203–212.
- Kazantsev A.V. Visual data processing and action control using binary neural network. Eight International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS’07), (Santorini, Greece, 6–8 June 2007). 2007. Р. 1–3. doi.org//10.1109/WIAMIS.2007.90.
- Liang S., Sun R., Li Y., Srikant R. Understanding the loss surface of neural networks for binary classification. Proc. of the 35th International Conference on Machine Learning. 2018. P. 2835–2843. URL: ttps://proceedings.mlr.press.
- Krinitskiy M., Verezemskaya P., Grashchenkov K., Tilinina N., Gulev S., Lazzara M. Deep convolutional neural networks capabilities for binary classification of polar mesocyclones in satellite mosaics. Atmosphere. 2018. Vol. 9, N 426. P. 1–23.
- Dunnmon J.A., Yi D., Langlotz C.P., RБ C., Rubin D.L., Lungren M.P. Assessment of convolutional neural networks for automated classification of chest radiographs. Radiology. 2018. Vol. 290, N 2. Р. 537–544. doi.org//10.1148/radiol.2018181422 .
- Korolev S., Safiullin A., Belyaev M., Dodonova Y. Residual and plain convolutional neural networks for 3d brain mri classification. arXiv:1701.06643v1 [cs.CV] 23 Jan 2017. URL: arxiv.org/pdf/1701.06643.pdf .
- Menon A.K., Williamson R.C., The cost of fairness in binary classification. Proc. of Machine Learning Research. 2018. Vol. 81. P. 1–12.
- Ferreyra-RamЗrez A., RodrЗguez-MartЗnez E., AvilБs-Cruz C., Lуpez-Saca F. Image retrieval system based on a binary auto-encoder and a convolutional neural network. IEEE Latin America Transactions. 2020. Vol. 18, Iss. 11. P. 1925–1932. doi.org//10.1109/TLA.2020.9398634.
- Litvinenko А. Algorithms for solution inference based on unified logical control models. Cybernetics and Systems Analysis. 2020. Vol. 56, N 2. P. 187–194.
