深度学习作为机器学习的一个新兴领域，与传统的机器学习相比，仍然存在一些问题。
Why are ConvNets a good architecture? – Scattering transform – Mark Tygert’s “complex ConvNet” How many layers do we really need? – Really? How many effective free parameters are there in a large ConvNet – The weights seem to be awfully redundant What about Local Minima? – Turns out almost all the local minima are equivalent – Local minima are degenerate (very flat in most directions) – Random matrix / spin glass theory comes to the rescue – [Choromanska, Henaff, Mathieu, Ben Arous, LeCun AI-stats 2015]
1.What’s Wrong With Deep Learning?
