A Unified Framework of Deep Neural Networks by Capsules
This work addresses the need for a unified theoretical foundation in deep learning, which could advance the field by improving model design and programming, though it appears incremental as it builds on existing capsule network concepts.
The authors tackled the problem of unifying the description of deep neural networks by developing a mathematical framework based on capsule networks and directed graph representations, proving a generation theorem about induced networks of connected directed acyclic graphs. The result is a unified framework that simplifies the description of existing deep neural networks and provides a theoretical basis for graphic designing and programming techniques in deep learning.
With the growth of deep learning, how to describe deep neural networks unifiedly is becoming an important issue. We first formalize neural networks mathematically with their directed graph representations, and prove a generation theorem about the induced networks of connected directed acyclic graphs. Then, we set up a unified framework for deep learning with capsule networks. This capsule framework could simplify the description of existing deep neural networks, and provide a theoretical basis of graphic designing and programming techniques for deep learning models, thus would be of great significance to the advancement of deep learning.