Experiment on creating a neural network with weights determined by the potential of a simulated electrostatic field

TL;DR

This paper demonstrates a novel method of setting neural network weights directly from electrostatic potential simulations, bypassing traditional training and analytical calculations, and validates its effectiveness on the MNIST dataset.

Contribution

It introduces a new approach to determine neural network weights using electrostatic potentials, eliminating the need for training algorithms or analytical solutions.

Findings

Neural networks can be initialized with weights derived from electrostatic potentials.

The method works effectively on the MNIST dataset.

Weights are obtained almost instantaneously without training procedures.

Abstract

This paper explores the possibility of determining the weights and thresholds of a neural network using the potential -- a parameter of an electrostatic field -- without analytical calculations and without applying training algorithms. The work is based on neural network architectures employing metric recognition methods. The electrostatic field is simulated in the Builder C++ environment. In the same environment, a neural network based on metric recognition methods is constructed, with the weights of the first-layer neurons determined by the values of the potentials of the simulated electrostatic field. The effectiveness of the resulting neural network within the simulated system is evaluated using the MNIST test dataset under various initial conditions of the simulated system. The results demonstrated functional viability. The implementation of this approach shows that a neural network can obtain weight values almost instantaneously from the electrostatic field, without the need for analytical computations, lengthy training procedures, or massive training datasets.