Version 1
: Received: 7 November 2023 / Approved: 7 November 2023 / Online: 7 November 2023 (11:25:29 CET)
How to cite:
Lutovac-Banduka, M.; Franc, I.; Milićević, V.; Zdravković, N.; Dimitrijević, N. Symbolic Analysis of Classical Neural Networks for Deep Learning. Preprints2023, 2023110446. https://doi.org/10.20944/preprints202311.0446.v1
Lutovac-Banduka, M.; Franc, I.; Milićević, V.; Zdravković, N.; Dimitrijević, N. Symbolic Analysis of Classical Neural Networks for Deep Learning. Preprints 2023, 2023110446. https://doi.org/10.20944/preprints202311.0446.v1
Lutovac-Banduka, M.; Franc, I.; Milićević, V.; Zdravković, N.; Dimitrijević, N. Symbolic Analysis of Classical Neural Networks for Deep Learning. Preprints2023, 2023110446. https://doi.org/10.20944/preprints202311.0446.v1
APA Style
Lutovac-Banduka, M., Franc, I., Milićević, V., Zdravković, N., & Dimitrijević, N. (2023). Symbolic Analysis of Classical Neural Networks for Deep Learning. Preprints. https://doi.org/10.20944/preprints202311.0446.v1
Chicago/Turabian Style
Lutovac-Banduka, M., Nemanja Zdravković and Nikola Dimitrijević. 2023 "Symbolic Analysis of Classical Neural Networks for Deep Learning" Preprints. https://doi.org/10.20944/preprints202311.0446.v1
Abstract
Deep learning is based on matrix computing with a large amount of hidden parameters that is not visible outside the computing module. Deep learning is a non-linear system and a linear approach is not possible. It is natural for people to visualize the algorithm and to follow some hidden parameters. In this paper, we propose a simple graphical programming of a nonlinear system based on drawing the simplest unit, such as a single neuron model. A more complex scheme of a classical neural network is obtained by commands copy-move-place of one neuron. The number of neurons and layers can be chosen arbitrarily. Once the scheme is complete, the implementation code is evaluated with symbolic parameters and nonlinear activation functions. This cannot be done manually. With the symbolic expression of outputs in terms of inputs and symbolic parameters, including symbolic activation pure functions, some other properties can be derived in closed form. This unique original approach can help scientists and developers and design numerical algorithms for machine learning and to understand how deep learning algorithms work.
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.