<abstract xmlns="http://www.w3.org/1999/xhtml"><p>The article discusses methods for accelerating the operation of convolutional neural networks for autonomous robotics learning. The analysis of the theoretical possibility of modifying the neural network learning mechanism is carried out. Classic semiotic analysis and the theory of neural networks is proposed to union. An assumption is made about the possibility of using the symmetry mechanism to accelerate the training of convolutional neural networks. A multilayer neural network to represent how space is an attempt has been made. The conclusion was based on the laws on the plane obtained earlier. The derivation of formulas turned out to be impossible due to the problems of modern mathematics. A new approach is proposed, which involves combining the gradient descent algorithm and the stochastic completion of convolutional filters by the principles of symmetries. The identified algorithms allow increasing the learning rate from 5% to 15%, depending on the problem that the neural network solves.</p></abstract>

The article discusses methods for accelerating the operation of convolutional neural networks for autonomous robotics learning. The analysis of the theoretical possibility of modifying the neural network learning mechanism is carried out. Classic semiotic analysis and the theory of neural networks is proposed to union. An assumption is made about the possibility of using the symmetry mechanism to accelerate the training of convolutional neural networks. A multilayer neural network to represent how space is an attempt has been made. The conclusion was based on the laws on the plane obtained earlier. The derivation of formulas turned out to be impossible due to the problems of modern mathematics. A new approach is proposed, which involves combining the gradient descent algorithm and the stochastic completion of convolutional filters by the principles of symmetries. The identified algorithms allow increasing the learning rate from 5% to 15%, depending on the problem that the neural network solves.

Convolutional Neural Networks Training for Autonomous Robotics

Kalashnikov Izhevsk State Technical University

Management Systems in Production Engineering

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Convolutional Neural Networks Training for Autonomous Robotics"}

The article discusses methods for accelerating the operation of convolutional neural networks for autonomous robotics learning. The analysis of the theoretical...

Convolutional Neural Networks Training for Autonomous Robotics

Online veröffentlicht: 02. Dez. 2020

Seitenbereich: 75 - 79

Eingereicht: 01. Aug. 2020

Akzeptiert: 01. Okt. 2020

DOI: https://doi.org/10.2478/mspe-2021-0010

Schlüsselwörter
autonomous robots, convolutional neural networks, learning, autoromorphisms, symmetry mechanism, semiotic analyze

© 2021 Alexander Lozhkin et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Convolutional Neural Networks Training for Autonomous Robotics

Online veröffentlicht: 02. Dez. 2020

Seitenbereich: 75 - 79

Eingereicht: 01. Aug. 2020

Akzeptiert: 01. Okt. 2020

DOI: https://doi.org/10.2478/mspe-2021-0010

Schlüsselwörterautonomous robots, convolutional neural networks, learning, autoromorphisms, symmetry mechanism, semiotic analyze

© 2021 Alexander Lozhkin et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
autonomous robots, convolutional neural networks, learning, autoromorphisms, symmetry mechanism, semiotic analyze