We can learn a lot about Why Deep Learning Works by studying the properties of the layer weight matrices of pre-trained neural networks.   And, hopefully,

Power Law Distributions in Deep Learning In a previous post, we saw that the Fully Connected (FC) layers of the most common pre-trained Deep Learning

Why Does Deep Learning Work ?    If we could get a better handle on this, we could solve some very hard problems in Deep Learning. A

Why Deep Learning Works: Self Regularization in DNNs An early talk describing details in this paper Implicit Self-Regularization in Deep Neural Networks: Evidence from Random

Rethinking Generalization: the Google paper Last year, ICLR 2017, a very interesting paper came out of Google claiming that Understanding Deep Learning Requires Rethinking Generalization

Please enjoy my video presentation on Geoff Hinton’s Capsule Networks.  What they are, why they are important, and how they are implemented (in Keras) …