In reference to the problem of constant memory training of RNNs, I mentioned the forward computation of derivatives in this talk (although I didn't know the name).Here is a recent paper I encountered that proposes an approximation to this method; it might be interesting to anyone who's interested in this problem.On Tue, Mar 8, 2016 at 12:16 PM, Jörg Bornschein <bornj@iro.umontreal.ca> wrote:_______________________________________________Hi,this Friday our tea-talk will be a bit more of an brain storming session and we'll have David Krueger present and discuss some research ideas.Title: Bayesian non-parametric discriminative freeze-thaw sequential GANs,and other half-baked research ideasWho: David KruegerWhen: Fri. March 11th, 14:30Where: AA 3195Looking forward to see you there!j
Lisa_labo mailing list
Lisa_labo@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo
_______________________________________________
Lisa_labo mailing list
Lisa_labo@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo