The Algebra of Two Dimensional Patterns

TL;DR

This paper introduces an algebraic framework for representing two-dimensional patterns using reciprocals of polynomials, aiming to improve neural network training efficiency over traditional pixel-wise methods.

Contribution

It proposes a novel algebraic approach to pattern representation that enhances training efficiency in neural networks compared to existing pixel-based techniques.

Findings

Algebraic representation simplifies pattern training.

Method reduces computational complexity.

Potential for improved neural network performance.

Abstract

The article presents an algebra to represent two dimensional patterns using reciprocals of polynomials. Such a representation will be useful in neural network training and it provides a method of training patterns that is much more efficient than a pixel-wise representation.