ReLu gives good results for deep learning: http://jmlr.org/proceedings/papers/v1...

		espadrine on April 13, 2016 \| parent \| context \| favorite \| on: Tinker with a Neural Network in Your Browser ReLu gives good results for deep learning: http://jmlr.org/proceedings/papers/v15/glorot11a/glorot11a.p.... 6 layers is the maximum that this demonstration allows, and they kept j small-ish to show that you don't need that many to have good results.