University of Cambridge > Talks.cam > Formalisation of mathematics with interactive theorem provers [COMING UP IN LENT TERM] > From benchmark-centric to human-centric: deep learning methods in the formalisation of mathematics

From benchmark-centric to human-centric: deep learning methods in the formalisation of mathematics

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

If you have a question about this talk, please contact Angeliki Koutsoukou-Argyraki.

A flurry of deep learning for mathematics advances have been made in recent years. However, disproportionally little adoption of deep learning is seen in the practice of formal mathematics. I will argue against the benchmark-centric mindset prevalent in the deep learning community, and present works that build on and enhance human experiences of formal mathematics.

This talk is part of the Formalisation of mathematics with interactive theorem provers [COMING UP IN LENT TERM] 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