Development of a Neural Network-Based Mathematical Operation Protocol for Embedded Hexadecimal Digits Using Neural Architecture Search (NAS)

TL;DR

This paper presents a neural network approach optimized by Neural Architecture Search for performing addition on embedded hexadecimal digits, aiming to improve efficiency in machine learning-based arithmetic operations.

Contribution

It introduces a novel NAS-driven method for designing neural networks specifically for hexadecimal addition, outperforming manually designed models.

Findings

Final testing loss of 0.2937 for the NAS-optimized model

Comparison shows NAS models outperform human-designed models

Demonstrates effectiveness of NAS in specialized arithmetic tasks

Abstract

It is beneficial to develop an efficient machine-learning based method for addition using embedded hexadecimal digits. Through a comparison between human-developed machine learning model and models sampled through Neural Architecture Search (NAS) we determine an efficient approach to solve this problem with a final testing loss of 0.2937 for a human-developed model.