COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |

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 - Friday 03 December 2021, 16:00-17:00
- Seminar Room 1, Newton Institute.
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. ## This talk is included in these lists:- All CMS events
- Featured lists
- INI info aggregator
- Isaac Newton Institute Seminar Series
- School of Physical Sciences
- Seminar Room 1, Newton Institute
- bld31
Note that ex-directory lists are not shown. |
## Other listsCambridge University Students Against Pseudoscience Educational Leadership, Policy, Evaluation and Change (ELPEC) Academic Group Cambridge Area Sequencing Informatics Meeting VI (2014)## Other talksBreak Engineering the future by leveraging digital technologies Talk 4 – Optimal Vaccine Allocation Strategies Within and Between Countries Gateway Exploring the Cold Universe: From Obscured Active Galactic Nuclei, Interstellar to Circumgalactic Media at z ~ 5 - 7 Disabled Staff Network Launch Event: Disability and the Impact of Covid |