University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Convolutional Neural Networks

  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

Convolutional Neural Networks

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

If you have a question about this talk, please contact Rowan McAllister.

Abstract: In this talk we outline convolutional neural networks (convnets) and discuss their contemporary applications and research. We begin by outlining prior assumptions and learning techniques for understanding data with a spatial structure. Secondly, we go through the key insights that have allowed convnets to surpass state-of-the-art performance in visual classification, regression, OCR , scene understanding and visual reinforcement learning.

Reading
  1. Jarrett et al., What Is the Best Multi-Stage Architecture for Object Recognition?
  2. Krizhevsky, Sutskever, and Hinton, ImageNet Classification with Deep Convolutional Neural Networks.
  3. Szegedy, et al. Going deeper with convolutions.

This talk is part of the Machine Learning Reading Group @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Rethinking Economic Development Models: Reflections on Pakistani Experience Cambridge AWiSE Biophysical Techniques Lecture Series 2016 Cambridge Neuroscience Seminar, 2011 The Eastern Counties Branch of The Welding Institute

Other talks

Transport and Settling of Sediments in River Plumes Imaging techniques and novel tools for early detection and intervention Borel Local Lemma CANCELLED IN SYMPATHY WITH STRIKE Nationality, Alienage and Early International Rights The MHC ligandome of two contagious cancers within the Tasmanian devil population, Devil Facial Tumour 1 and Devil Facial Tumour 2 Quantifying Uncertainty in Turbulent Flow Predictions based on RANS/LES Closures
 

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