KEYWORD |
Enriching model assessments to facilitate human intervention/agency in AI model development and monitoring
Thesis in external company
keywords ALGORITHM FAIRNESS, ARTIFICIAL INTELLIGENCE, DATA ETHICS, DATA QUALITY, DATA SCIENCE, EXPLAINABLE AI, HUMAN-COMPUTER INTERACTION, SOFTWARE ENGINEERING
Reference persons JUAN CARLOS DE MARTIN, ANTONIO VETRO'
Research Groups DAUIN - GR-22 - Nexa Center for Internet & Society - NEXA
Thesis type EXPEIRMENTAL, IN COMPANY, INDUSTRIAL, RESEARCH / EXPERIMENTAL, RESEARCH THESIS WITH A COMPANY, RESEARCH, INNOVATIVE
Description While generating explanation based assessments for blackbox AI models is not very complicated, presenting that information to humans in a way that they can make positive interventions within the datasets and models is not straightforward. We are interested in understanding the best practices to provide augmented cues to model builders to make their AI models more human centric, trustworthy and controllable.
Clearbox AI is an innovative SME, incubated in I3P, winner of the National Innovation Award (PNI 2019) in the ICT category and the EU Seal of Excellence awarded by the European Commission. Clearbox AI is developing a unique and innovative technology ("AI Control Room"), which allows to put into production artificial intelligence models that are robust, explainable and monitorable over time.
See also https://clearbox.ai/ai-control-room/
Deadline 08/10/2022
PROPONI LA TUA CANDIDATURA