University of Cambridge > Talks.cam > NLIP Seminar Series > Continuous feature structures: Can we learn structured representations with neural networks?

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Continuous feature structures: Can we learn structured representations with neural networks?

Download to your calendar using vCal

If you have a question about this talk, please contact Andrew Caines .

The basic data structure for neural network models is the vector. While this is computationally efficient, vector representations require a fixed number of dimensions, which makes it impossible to encode even basic data structures that would be familiar to a first-year undergraduate, such as lists, trees, and graphs. In this talk, I will focus on feature structures, a general-purpose data structure which is notably used in HPSG grammars. One challenge with learning such structured representations is that they are discrete, which rules out training with gradient descent. In this talk, I will present a continuous relaxation of feature structures, which allows them to be used in neural networks trained by gradient descent. In particular, I will show how these continuous feature structures can replace vectors in an LSTM , which would make it possible to learn feature structure representations of sentences.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHptUXlRSkppQT09 Coslett (COS207), Anglia Ruskin University, Cambridge Hicks & Mead Rooms, University Centre, Granta Place

Other talks

The rise of local cartography in Europe, 12th-14th century The elephant in the room: Machine Learning directly into physical models The Magic of Magnetism Online Causal Inference Semina Title to be confirmed Harnessing Radical Reactivity for Molecular Innovation
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity