~1 min read
There's some really great stuff in this article. In concept I get Deep Learning but there's so much more below the surface. I agree that there needs to be some sort of unification of architecture but IMHO that can occur after the explosion of innovation starts to slow down. It's a wild wild west out there right now, let's see who turns out to be sheriff.
Deep Learning Architecture can be described as a new method or style of building machine learning systems. Deep Learning is more than likely to lead to more advanced forms of artificial intelligence. The evidence for this is in the sheer number of breakthroughs that had occurred since the beginning of this decade. There is a new found optimism in the air and we are now again in a new AI spring. Unfortunately, the current state of deep learning appears too many ways to be akin to alchemy. Everybody seems to have their own black-magic methods of designing architectures. The field thus needs to move forward and strive towards chemistry, or perhaps even a periodic table for deep learning. Although deep learning is still in its early infancy of development, this book strives towards some kind of unification of the ideas in deep learning. It leverages a method of description called pattern languages. via Deep Learning Patterns
The Periodic Table of Deep Learning is a nice touch!