A Novel Browser-based No-code Machine Learning Application Development Tool

Abstract

Machine learning (ML) application development constitutes a complex process that requires developers to have considerable amount of programming and specialized technical skills. There is still a substantial barrier for researchers who do not possess the programming and technical skills to develop ML models that meets the needs of their specific fields of study. The typical ML model development workflow entails the installation of a set of software elements and a certain amount of code development. This paper introduces a browser-based ML application development tool that is geared towards the needs of researchers who have limited knowledge in programming. The tool allows the users to create a customized image classifier model based on the image sets that they provide. The tool provides a no-code workflow that enables users to create and test their ML models on a browser without downloading any software modules.