Research on available tools for testing Machine Learning-based systems.

• Grant number: 23/05483-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2023
• End date: December 31, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Agreement: MCTI/MC
• Principal Investigator: Flávio Soares Corrêa da Silva
• Grantee: Rafael de Oliveira Magalhães
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Company: Secretaria de Desenvolvimento Econômico (São Paulo - Estado). Instituto de Pesquisas Tecnológicas S/A (IPT)
• Associated research grant: 20/09850-0 - Applied Artificial Intelligence Research Center: accelerating the evolution of industries toward standard 5.0, AP.PCPE

Abstract

The project aims to study testing tools for Machine Learning-based systems. To achieve this goal, a neural network model for traffic forecasting, described in a scientific paper and which obtained good results through training with data from a specific city or region, will be selected and employed to experiment with the tools. Such neural network will be trained with data from other regions, which will allow verifying the model's robustness and the use of testing tools with data that have different granularities and physical and temporal dependencies, and which may contain irregularities or be incomplete.This project is expected to evaluate the robustness and scalability of testing tools, as well as to enable greater reliability of Machine Learning-based systems through testing and knowledge of the suitability of training data and the adaptability of both the neural network and tests to variations in data.