University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > The Representation Theory of Neural Networks (copy)

The Representation Theory of Neural Networks (copy)

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

If you have a question about this talk, please contact nobody.

MDL - Mathematics of deep learning

In this talk, I will present how the representation theory of quivers can be used to study artificial neural networks. We will start by looking at why neural networks are pairs of a quiver representation and an activation function and how a neural network computes an output for a given input. We will then translate the computations of a neural network into a quiver representation and show how these induced quiver representations can be viewed inside a moduli space and finally how the training dynamics of a neural network can be translated to this moduli space.

This talk is part of the Isaac Newton Institute Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity