Experiment on creating a neural network with weights determined by the potential of a simulated electrostatic field
This is an incremental approach for neural network design that could simplify weight initialization in specific applications.
The paper tackled the problem of determining neural network weights without training by using potentials from a simulated electrostatic field, and demonstrated functional viability on MNIST with near-instantaneous weight assignment.
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.