Titulo Estágio
Development of a Comprehensive Model Audit Framework
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
DEI
Enquadramento
This research proposal aims to develop a comprehensive model audit framework to ensure the quality of the trainning machine learning model used in an Artificial Intelligent systems. The framework will provide a systematic approach to evaluating and improving quality of the model, addressing issues such as hyperparameterization optimization.
Objetivo
To design a model audit framework that systematically evaluates model quality across multiple dimensions, including hyperparameterization optimization issues.
To validate the effectiveness of the framework through case studies and empirical analysis in various application domains, such as healthcare, finance, and social media.
Plano de Trabalhos - Semestre 1
Literature Review: Conduct a comprehensive review of existing model audit frameworks, tools, and techniques to identify best practices and gaps in current approaches.
Dataset Selection: Conduct a thorough search for potential datasets from various sources, such as (but not limited to) public repositories
Framework Design Mockups: Develop the mockups of the audit framework that outline the different levels of the user interface.
Writing the interim report
Plano de Trabalhos - Semestre 2
Framework Development: Create software framework to automate the model auditing process, incorporating machine learning techniques for leading with hyperparameter optimization problems.
Case Studies: Apply the framework to different datasets in various application domains.
Analyze the results to assess the effectiveness of the framework in improving the quality of the developed model.
Writing the final report
Condições
.
Observações
.
Orientador
Pedro Henriques Abreu
pha@dei.uc.pt 📩