Titulo Estágio
Detection of Societal Bias in Intelligent Models
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
CISUC
Enquadramento
Nowadays intelligent systems increasingly determine whether someone gets a job or a loan, how much they’re paid, how they’re treated by doctors and hospitals, and how fairly they’re dealt with by government, law enforcement, and the justice system.
https://spectrum.ieee.org/artificial-intelligence/machine-learning/engineering-bias-out-of-ai
The European Union recently proposed a law that wants to regulate the use of technology so that citizens can have confidence in the use of Artificial Intelligence systems and, for that, it establishes the minimum compliance limits to which the providers of this technology must be subject.
Engineers and scientists developing AI systems are focusing more and more their attention on Explainable Artificial Intelligence (XAI) methods that will enable them to gain confidence with system outcomes and, as a consequence, build user trust. There is a strong emergence for a unified and high-level methodology to classify AI products as partially or fully explainable.
Objetivo
In this internship the student should study, propose, implement, and test models for detection of societal bias in intelligent models.
To achieve this goal, the following objectives will be pursued:
- Study the state of the art
- Study the available datasets for societal bias
- Study the available frameworks for model development
- Define, implement, and fine tune the learning architecture
- Propose and deploy test setup
Plano de Trabalhos - Semestre 1
- Literature review
- Identification of datasets sources for model development
- Identification and study of available frameworks for model development
- Define the architecture of the system
- Start implementing the proposed approach
- Write intermediate report
Plano de Trabalhos - Semestre 2
- Implement the proposed solution and fine tune models
- Test and evaluate performance
- Write scientific article
- Write final report
Condições
This work should take place in the context of a research project in a CISUC lab.
There is the possibility of a 3/6-month scholarship from CISUC.
Observações
During the application phase, doubts related to this proposal, namely regarding the objectives and conditions, should be clarified with the advisors, by e-mail (catarina@dei.uc.pt) or a meeting to be arranged after a contact by email.
Orientador
Catarina Silva, Bernardete Ribeiro, Joana Costa
catarina@dei.uc.pt 📩