Neural networks with image recognition by pairs

TL;DR

This paper introduces a neural network approach that recognizes images in pairs, simplifying training and expanding capabilities without analytical weight calculations, enabling scalable and transparent image recognition.

Contribution

It presents a novel pairwise recognition neural network that can be trained with classical algorithms, avoiding complex analytical weight computations and allowing easy network expansion.

Findings

Simplified network architecture and training process.

Ability to recognize a large number of images.

Scalable increase in recognizable classes without altering existing weights.

Abstract

Neural networks based on metric recognition methods have a strictly determined architecture. Number of neurons, connections, as well as weights and thresholds values are calculated analytically, based on the initial conditions of tasks: number of recognizable classes, number of samples, metric expressions used. This paper discusses the possibility of transforming these networks in order to apply classical learning algorithms to them without using analytical expressions that calculate weight values. In the received network, training is carried out by recognizing images in pairs. This approach simplifies the learning process and easily allows to expand the neural network by adding new images to the recognition task. The advantages of these networks, including such as: 1) network architecture simplicity and transparency; 2) training simplicity and reliability; 3) the possibility of using a large number of images in the recognition problem using a neural network; 4) a consistent increase in the number of recognizable classes without changing the previous values of weights and thresholds.