A Capsule-unified Framework of Deep Neural Networks for Graphical Programming
This work provides a theoretical framework for unifying deep learning models, potentially aiding in graphical programming tools, but it appears incremental as it builds on existing capsule and graph concepts without demonstrating broad practical impact.
The authors tackled the problem of unifying the description of diverse deep neural networks by formalizing them mathematically and representing them as directed graphs, then extended this with a capsule-based framework to include a universal backpropagation algorithm and graphical programming applications.
Recently, the growth of deep learning has produced a large number of deep neural networks. How to describe these networks unifiedly is becoming an important issue. We first formalize neural networks in a mathematical definition, give their directed graph representations, and prove a generation theorem about the induced networks of connected directed acyclic graphs. Then, using the concept of capsule to extend neural networks, we set up a capsule-unified framework for deep learning, including a mathematical definition of capsules, an induced model for capsule networks and a universal backpropagation algorithm for training them. Finally, we discuss potential applications of the framework to graphical programming with standard graphical symbols of capsules, neurons, and connections.