Machine learning, neural networks

Algorithm for calculating the weight values of a convolutional neural network without training

P. Sh. Geidarov

Institute of Control Systems, Ministry of Science and Education of the Republic of Azerbaijan

Abstract: This study provides a description of the algorithm on the basis of which weights and thresholds are analytically calculated, as well as the number of channels in the layers of a convolutional neural network. Based on the proposed algorithm, a number of experiments were carried out with recognition of the MNIST database. The results of the experiments described in the work showed that the time for calculating the weights of convolutional neural networks is relatively short and amounts to fractions of a second or a minute. The experimental results also showed that already using only 10 selected images from the MNIST database, analytically calculated convolutional neural networks are able to recognize more than half of the images of the MNIST test database, without using neural network training algorithms. Preliminary analytical calculation of the value of the weights of a convolutional neural network allows to speed up the training procedure of a convolutional neural network.

Keywords: deep neural networks, convolutional neural networks, pattern recognition, MNIST database, calculating the weights of neural networks, calculating the kernels of convolutional layers, training a neural network.

DOI: 10.14357/20718594240305

Bibliographic databases:

•