University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > 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

ℹ️ 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 Mateja Jamnik .

Notice unusual day, time and room

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.

Zoom link for online participants, Meeting ID: 659 082 2098 Passcode: 1dYRka

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

King's College, Cambridge: the Audit Room. Senior Parlour, Gonville & Caius College Faculty of Education, 184 Hills Road, Cambridge, CB2 8PQ, (room TBC Donald McIntyre Building)

Other talks

Machine Learning for Spectral Geometry and Vice Versa What’s my reproduction number? Life history strategies: an interdisciplinary perspective TBC Together Now: Cooperation and Collaboration in Social Art Practice Morning Tea and Coffee Morning Break
 

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