University of Cambridge > Talks.cam > CBL Research Talks > An Alternative to Backpropagation

  Browse A-Z

Log in

University Account External (via Google)

šŸ” Log In

Information on

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

ā„¹ļø Information

An Alternative to Backpropagation

Download to your calendar using vCal

If you have a question about this talk, please contact Cat Spencer .

For decades, backpropagation has been the backbone of deep learning. However, it is biologically implausible, computationally demanding, and sometimes inefficient. This has spurred the search for alternative training paradigms. I will introduce a novel gradientā€‘free approach in which the objective is to align the distribution of a networkā€™s linear regions with that of the training data. On CIFAR ā€‘10, this approach surpasses the performance achieved by Adam, which demonstrates that carefully structuring a modelā€™s linear regimes can provide a powerful alternative to traditional gradientā€‘based methods.

This talk is part of the CBL Research Talks series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

My seminars Cambridge Centre for Brain Repair LCHES Seminars on Human Evolution

Other talks

Title to be confirmed Zooming in on the assembly of galaxies in the early Universe Group Work Morning Break / Group Photo Coexisting with carnivores? The lynx and wolf reintroduction debate Title TBC
 

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