Work

Explaining the black-box or using the black-box to develop better interpretable solutions?

Year: 2025

Type: article

Abstract: Understanding the decision-making processes behind Artificial Intelligence models became a crucial aspect of AI. This paper describes a study that compares the performance of models produced by both interpretable and black-box algorithms and evaluates if it is possible to use black-box models to assist in interpretable models' training. We verified a significant difference in performance between the two types of models. However, the interpretable model was able to mimic the behavior of the black-box models to a satisfactory degree. The promising initial results obtained from using black-box models to aid in interpretable models' training suggest the potential efficacy of this approach.

Source: Revista Brasileira de Computação Aplicada

DOI: 10.5335/rbca.v17i2.16459

Authors: Vinicius Alves Matias, Julia Machado Lechi, Norton Trevisan Roman, Luciano Antonio Digiampietri

Institution: Universidade de São Paulo

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W4413880122

FWCI:

Cites:

Cited by:

Related to: 10