The goal of trustworthy AI is to develop reliable, fair, transparent, and secure artificial intelligence systems aligned with human values and ethical principles. Differential replication through copying refers to the process of replicating the decision behavior of a machine learning model using another model that possesses enhanced features and attributes. This process is relevant when already deployed machine learning models do not align with trustworthy AI design principles. Under such circumstances, copying enables the retention of original prediction capabilities while adapting to new demands without requiring an expensive model retraining, allowing companies to fulfill the trustworthy AI principles more simply.
Presential in the seminar room. Zoom link:
https://zoom.us/j/98286706234?pwd=bm1JUFVYcTJkaVl1VU55L0FiWDRIUT09
Coffee and cookies will be served 15 minutes before the start of the seminar
Contact details:
Jose Javier Ramasco Contact form