University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > MDL Reading Group

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

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

ℹ️ Information

MDL Reading Group

Download to your calendar using vCal

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

MDL - Mathematics of deep learning

I will present the paper “A mean field limit for certain deep neural networks” by DYEGO ARA ÚJO, ROBERTO I . OLIVEIRA & DANIEL YUKIMURA . 

I recent years, increased attention has been paid to DNNs with high numbers of parameters, after observations that the classical bias-variance tradeoff principle fails to paint an accurate picture of the behaviour of NNs as the dimension of their parameter space tends to infinity. This motivated several lines of reasearch into the limiting behaviour of NNs under various scaling frameworks. 

The paper above presents a self contained and intuitive description of this phenomenon. I’ll try to shine some light under the complex notation and to explain the major ideas behind the results. 

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

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

FW11, William Gates Building. Zoom link: https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=addon Atrium, Alison Richard Building, West Road hc446

Other talks

Title to be confirmed Title to be confirmed Using A Function-Centric Lens to Re-consider Regularisation, Representation Transfer and Geometric Properties of Neural Networks Title to be confirmed: The Ghost Collider Title TBC Topic Film, TV shows for Medical Education, ‘The Wire’ as a case study
 

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