University of Cambridge > Talks.cam > NLIP Seminar Series > Learning Tensors and Random Matrix Theory

Learning Tensors and Random Matrix Theory

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

If you have a question about this talk, please contact James Thorne.

Type-driven compositional distributional semantics interprets grammatical types of a system such as the CCG as tensor spaces and words of that type as elements therein. It offers a canonical way of composing the tensors, via tensor contraction. There is much less known about the characteristics of the tensors: is there a canonical way of building them and what statistical rules govern their distribution? Based on recent joint work with Wijnholds and Clark and with Kartsaklis, Ramgoolam and Sword, we provide some answers.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity