PPT-Dougal Sutherland, 9/25/13

Problem with regular RNNs The standard learning algorithms for RNNs dont allow for long time lags Problem error signals going back in time in BPTT RTRL etc either

error experiment lstm memory experiment error memory lstm works exponential noise output cells input decay learning sequence add time

Presentation Embed Code

<iframe width="560" height="315" src="https://www.docslides.com/embed/437145" frameborder="0" allowfullscreen></iframe>

Download Presentation

Download Presentation The PPT/PDF document "Dougal Sutherland, 9/25/13" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.