Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Last revision Both sides next revision
replay [2018/10/01 12:40]
admin
replay [2018/10/02 20:22]
admin
Line 12: Line 12:
  
 We investigate the effects of parameter lag resulting in representational drift and recurrent state staleness and empirically derive an improved training strategy. ​ We investigate the effects of parameter lag resulting in representational drift and recurrent state staleness and empirically derive an improved training strategy. ​
 +
 +https://​arxiv.org/​abs/​1809.10635v1 Generative replay with feedback connections as a general strategy for continual learning