University of Cambridge > Talks.cam > CamPoS (Cambridge Philosophy of Science) seminar > What kind of models are deep learning algorithms?

What kind of models are deep learning algorithms?

Download to your calendar using vCal

  • UserLena Zuchowski (University of Bristol)
  • ClockWednesday 03 March 2021, 13:00-14:30
  • HouseZoom.

If you have a question about this talk, please contact Matt Farr .

I will introduce a novel conceptual framework for the analysis of scientific modelling. The framework will be used to distinguish and comparatively analyse three different ways of model construction: vertical from covering theory and empirical knowledge about a given target system; horizontal through the systematic variation or transfer of existing models; and diagonal through a combination of vertical and horizontal construction steps. I will then apply this framework to analyse the construction of deep learning algorithms and will argue that they can be interpreted as the automated, vertical, bottom-up construction of a sequence of scientific models. Furthermore, I will maintain that the practice of transfer learning can be interpreted as horizontal model construction.

This talk is part of the CamPoS (Cambridge Philosophy of Science) seminar series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

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