?Deep Learning is presented as Energy-Based Learning Indeed, we train a neural network by running BackProp, thereby minimizing the model error–which is like minimizing an Energy. But

A friend from grad school pointed out a great foundational paper on Boltzmann Machines.  It is a 1987 paper from complex systems theory A Mean

Restricted Boltzmann Machines (RBMs) are like the H atom of Deep Learning. They are basically a solved problem, and while of academic interest, not really used

Why Deep Learning Works: Perspectives from Theoretical Chemistry:

“Why does deep and cheap learning work so well?“ This is the question posed by a recent article.  Deep Learning seems to require knowing the Partition