University of Cambridge > Talks.cam > Mathematics and Computation > Deep-layered machines have a built-in Occam's razor

  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

ℹī¸ Information

Deep-layered machines have a built-in Occam's razor

Download to your calendar using vCal

If you have a question about this talk, please contact Challenger Mishra .

Input-output maps are prevalent throughout science and technology. They are empirically observed to be biased towards simple outputs, but we don’t understand why. To address this puzzle, we study the archetypal input-output map: a deep-layered machine in which every node is a Boolean function of all the nodes below it. We give an exact theory for the distribution of outputs, and we confirm our predictions through extensive computer experiments. As the network depth increases, the distribution becomes exponentially biased towards simple outputs. This suggests that deep-layered machines and other learning methodologies may be inherently biased towards simplicity in the models that they generate.

Preprint: https://arxiv.org/abs/2603.01217

Zoom: https://cl-cam-ac-uk.zoom.us/j/6590822098 Meeting ID: 659 082 2098 Passcode: 1dYRka

This talk is part of the Mathematics and Computation series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Room 6.12a, Malet Place Engineering Building, UCL Statistical Laboratory, Centre for Mathematical Sciences, University of Cambridge Average on weekdays: 8851.025 kWh

Other talks

Cambridge RNA Club - ONLINE Sera Markoff Inaugural Lecture for the Plumian Professorship in Astronomy and Experimental Philosophy - 'Staring into the heart of darkness: from theory to the direct imaging of black holes' Morning Break / Group Photo Title to be confirmed Scattering Plenty: the people who made the modern countryside Bigger Picture Talk: Developing future marine engines running on ammonia and other green fuels
 

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