The Algebra of Two Dimensional Patterns

2011/02/22 by Subhash Kak, Kak, Subhash · 1 citation
Computer Science · Mathematics · #FOS: Computer and information sciences #Image Retrieval and Classification Techniques #Image and Object Detection Techniques #Information Theory (cs.IT) #Neural Networks and Applications #cs.IT #math.IT

paper · pdf · doi:10.48550/arxiv.1102.4573

11 pages, 14 figures

arxiv created 2011/02/22 · openalex publication_date 2011/02/22 · arxiv updated 2011/02/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Unary Coding for Neural Network Learning

Cited by

• Two Dimensional Random Patterns

Related

• Multilayer Perceptron Algebra
• nn2poly: An R Package for Converting Neural Networks into Interpretable Polynomials
• An Algorithm for Training Polynomial Networks
• A logical re-conception of neural networks: Hamiltonian bitwise part-whole architecture
• Algebraic Machine Learning: Learning as computing an algebraic decomposition of a task