Stacked Approximated Regression Machine: A Simple Deep Learning Approach

Re:Stacked Approximated Regression Machine: A Simple Deep Le... by jcannell on Tuesday September 06, 2016 @12:01PM (#12436949)

This is a pretty good summary, but to note this is not a new unsupervised technique - it's a sparse coding method, and sparse coding has been around for more than a decade. Summarizing this paper without mentioning the word sparse coding seems wrong somehow. ;)

[ Parent | on HN ]

Re:Stacked Approximated Regression Machine: A Simple Deep Le... by cs702 on Tuesday September 06, 2016 @04:30PM (#12439082)

You're right, sparse coding is not new -- and neither is the idea of greedy layer-wise training.

But if this works as advertised, these guys must be doing something new.

[ Parent | on HN ]

Re:Stacked Approximated Regression Machine: A Simple Deep Le... by saguppa on Friday September 09, 2016 @11:01AM (#12462831)

But, sadly, it doesn't work as advertised. My hypothesis is that it's extremely difficult to get great results with greedy training. Jointly learning multiple layers from huge datasets is why things started working so well.

[ Parent | on HN ]

Re:Stacked Approximated Regression Machine: A Simple Deep Le... by cs702 on Friday September 09, 2016 @01:43PM (#12464424)

Yes, I just saw the retraction.

[ Parent | on HN ]