Nicolas Vayatis - Deep Out-of-the-distribution Uncertainty Quantification in for Data (...) скачать в хорошем качестве

Nicolas Vayatis - Deep Out-of-the-distribution Uncertainty Quantification in for Data (...)

In this talk, we present a practical solution to the lack of prediction diversity observed recently for deep learning approaches when used out-of-distribution. Considering that this issue is mainly related to a lack of weight diversity, we introduce the maximum entropy principle for the weight distribution coupled with the standard, task-dependent, in-distribution data fitting term. We prove numerically that the derived algorithm is systematically relevant. We also plan to us this strategy to make out-of-distribution predictions about the future of data (science) scientists. Nicolas Vayatis (ENS Paris-Saclay) === Find this and many more scientific videos on https://www.carmin.tv/ - a French video platform for mathematics and their interactions with other sciences offering extra functionalities tailored to meet the needs of the research community. ===