University of Cambridge > Talks.cam > Darwin College Science Seminars > Popper meets machine learning - How falsificationism can guide the design of AI solutions

Popper meets machine learning - How falsificationism can guide the design of AI solutions

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Laura Pellegrini.

Machine learning pushes the frontiers of algorithmic achievements, though the strive for state-of-the-art performance often obscures the fragility of enforcing decisions among uncertainty. This talk interprets machine learning within Karl Popper’s epistemology and assesses machine learning paradigms’ fit for falsificationism and argues that the new interpretation can improve robustness by guiding the design of how AI is deployed in practice. Though the price is to accept unambiguous decisions, the restriction of the outcomes still adds value. The context for our work is established by comparison with similar techniques and highlighting its limitations.

This talk is part of the Darwin College Science Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2023 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity