University of Cambridge > Talks.cam > Machine Learning Study Group > Deep Learning Book - Meeting 5 - ResNets and DenseNets

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

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

Deep Learning Book - Meeting 5 - ResNets and DenseNets

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Alessandro Davide Ialongo.

In this meeting we aim to cover some recent advances in Convolutional Neural Networks (which were first covered last week in Chapter 9 of the Deep Learning Book):

ResNets: https://arxiv.org/abs/1512.03385

DenseNets: https://arxiv.org/abs/1608.06993

Please read the material before attending the meeting.

Time allowing, we will watch the following video on networks with stochastic depth:

https://channel9.msdn.com/Events/Neural-Information-Processing-Systems-Conference/Neural-Information-Processing-Systems-Conference-NIPS-2016/Deep-Learning-Symposium-Session-2

This talk is part of the Machine Learning Study Group series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Business Briefings: International Seminar Series 2015-16 Cambridge Conversations in Translation CU Explorer's Society Cambridge Judge Business School Mechanisms of Language Change Research Cluster – student run event 2012 Human-Computer Interaction

Other talks

Overview of Research Process Making Refuge: Cambridge & the Refugee Crisis Modelling discontinuities in simulator output using Voronoi tessellations Translational Science: using biomarkers to guide clinical development in oncology Reforming the Chinese Electricity System: A Review of the Market Reform Pilot in Guangdong Group covariance functions for Gaussian process metamodels with categorical inputs
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity