What Really is Deep Learning Doing?
This is an incremental theoretical analysis for researchers seeking to understand deep learning mechanisms.
The paper tackles the open question of what deep learning is really doing by viewing it from the perspective of mechanical learning and learning machine, aiming to explain why it works well, how it works, and data requirements, but does not provide concrete results or numbers.
Deep learning has achieved a great success in many areas, from computer vision to natural language processing, to game playing, and much more. Yet, what deep learning is really doing is still an open question. There are a lot of works in this direction. For example, [5] tried to explain deep learning by group renormalization, and [6] tried to explain deep learning from the view of functional approximation. In order to address this very crucial question, here we see deep learning from perspective of mechanical learning and learning machine (see [1], [2]). From this particular angle, we can see deep learning much better and answer with confidence: What deep learning is really doing? why it works well, how it works, and how much data is necessary for learning. We also will discuss advantages and disadvantages of deep learning at the end of this work.