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
compression [2018/09/09 13:20]
admin
compression [2018/10/24 10:43]
admin
Line 88: Line 88:
  
 This might explain the relatively poor practical performance of variational methods in deep learning. On the other hand, simple incremental encoding methods yield excellent compression values on deep networks, vindicating Solomonoff'​s approach. This might explain the relatively poor practical performance of variational methods in deep learning. On the other hand, simple incremental encoding methods yield excellent compression values on deep networks, vindicating Solomonoff'​s approach.
 +
 +https://​arxiv.org/​abs/​1810.09274v1 From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference
 +