Preconceitos presentes na sociedade podem criar vieses em modelos aprendidos a partir de dados. Para avaliar a existência de viés, alguns pesquisadores propõem o uso de definições de \"justiça\", enquanto outros usam técnicas de interpretabilidade. Porém, parece não existir nenhum estudo que compara as medidas de justiça (através de várias definições de justiça) e os resultados de interpretabilidade (através de várias noções de interpretabilidade). Nesse trabalho foi proposto metodologias para examinar e comparar essas técnicas. A ideia ´e avaliar como as medidas de justiça e o resultado de interpretabilidade variam em um modelo com viés e em outro sem viés. O foco foi no uso do SHAP (SHapley Additive exPlanations) como técnica de interpret...
Algorithm fairness has become a central problem for the broad adoption of artificial intelligence. A...
While machine learning models have achieved unprecedented success in real-world applications, they m...
International audienceFairness emerged as an important requirement to guarantee that Machine Learnin...
Machine Learning has become more and more prominent in our daily lives as the Information Age and Fo...
With the rise of deep learning and complex machine learning algorithms, higher performance has been ...
International audienceFairness of algorithms is the subject of a large body of literature, of guides...
Addressing the problem of fairness is crucial to safely use machine learning algorithms to support d...
International audienceAutomated decision systems are increasingly used to take consequential decisio...
Atualmente técnicas de aprendizado de máquina vêm sendo constantemente utilizadas para apoiar no pro...
Nowadays, it is widely recognized that algorithms risk to reproduce and amplify human bias that hist...
Over the last years, a wide spread of Machine Learning in increasingly more, especially sensitive ar...
Important decisions are increasingly based directly on predictions from classifiers; for example, ma...
Machine learning algorithms can produce biased outcome/prediction, typically, against minorities and...
The increasingly frequent use of Artificial Intelligence in the field of law, forces us to consider ...
Machine learning algorithms are widely used in management systems in different fields, such as emplo...
Algorithm fairness has become a central problem for the broad adoption of artificial intelligence. A...
While machine learning models have achieved unprecedented success in real-world applications, they m...
International audienceFairness emerged as an important requirement to guarantee that Machine Learnin...
Machine Learning has become more and more prominent in our daily lives as the Information Age and Fo...
With the rise of deep learning and complex machine learning algorithms, higher performance has been ...
International audienceFairness of algorithms is the subject of a large body of literature, of guides...
Addressing the problem of fairness is crucial to safely use machine learning algorithms to support d...
International audienceAutomated decision systems are increasingly used to take consequential decisio...
Atualmente técnicas de aprendizado de máquina vêm sendo constantemente utilizadas para apoiar no pro...
Nowadays, it is widely recognized that algorithms risk to reproduce and amplify human bias that hist...
Over the last years, a wide spread of Machine Learning in increasingly more, especially sensitive ar...
Important decisions are increasingly based directly on predictions from classifiers; for example, ma...
Machine learning algorithms can produce biased outcome/prediction, typically, against minorities and...
The increasingly frequent use of Artificial Intelligence in the field of law, forces us to consider ...
Machine learning algorithms are widely used in management systems in different fields, such as emplo...
Algorithm fairness has become a central problem for the broad adoption of artificial intelligence. A...
While machine learning models have achieved unprecedented success in real-world applications, they m...
International audienceFairness emerged as an important requirement to guarantee that Machine Learnin...