Re:Scientists See Promise in Deep-Learning Programs
by iskander on Saturday November 24, 2012 @03:10PM
(#4826306)
Boosting selects successive weak learners for the same classification problem, but under a changing distribution/weighting of the input space. Deep learning stacks complex models to create increasingly abstract representations. All I can really imagine them having in common is (1) they're both families of machine learning techniques and (2) they both (roughly) involve a collection of models, albeit in very different ways.
[ Parent
| on HN ]
Re:Scientists See Promise in Deep-Learning Programs
by mbq on Saturday November 24, 2012 @03:31PM
(#4826361)
You're talking about Adaboost; general boosting can use any models and the only idea there is that it adds new model to fix residuals of the current chain. BTW "increasingly abstract representation" is a perfect example of this meaningless PR ANNs are built of.
Re:Scientists See Promise in Deep-Learning Programs
by wookietrader on Saturday November 24, 2012 @03:36PM
(#4826379)
No.
Deep learning is not about fixing the residuals of the current chain. Deep learning isn't even about residuals in the first place. It's about (1) finding good representations of your data (aka feature learning), (2) then adding a discriminative model on top and then (3) tuning everything. There is no relation to boosting at all.