AI2: The next leap toward native language based and explainable machine learning framework

TL;DR

AI$^{2}$ introduces a natural language interface for machine learning, enabling non-experts to use algorithms via English commands, with added features for environmental awareness, data preprocessing, and explainability, advancing user-friendly AI tools.

Contribution

The paper presents a novel framework that allows machine learning algorithms to be accessed through natural language, incorporates GHG evaluation, and enhances explainability for broader usability.

Findings

User can call algorithms using English commands

Framework evaluates and suggests energy-efficient alternatives

Provides explanations with texts, graphics, and tables

Abstract

The machine learning frameworks flourished in the last decades, allowing artificial intelligence to get out of academic circles to be applied to enterprise domains. This field has significantly advanced, but there is still some meaningful improvement to reach the subsequent expectations. The proposed framework, named AI$^{2}$, uses a natural language interface that allows a non-specialist to benefit from machine learning algorithms without necessarily knowing how to program with a programming language. The primary contribution of the AI$^{2}$ framework allows a user to call the machine learning algorithms in English, making its interface usage easier. The second contribution is greenhouse gas (GHG) awareness. It has some strategies to evaluate the GHG generated by the algorithm to be called and to propose alternatives to find a solution without executing the energy-intensive algorithm. Another contribution is a preprocessing module that helps to describe and to load data properly. Using an English text-based chatbot, this module guides the user to define every dataset so that it can be described, normalized, loaded and divided appropriately. The last contribution of this paper is about explainability. For decades, the scientific community has known that machine learning algorithms imply the famous black-box problem. Traditional machine learning methods convert an input into an output without being able to justify this result. The proposed framework explains the algorithm's process with the proper texts, graphics and tables. The results, declined in five cases, present usage applications from the user's English command to the explained output. Ultimately, the AI$^{2}$ framework represents the next leap toward native language-based, human-oriented concerns about machine learning framework.