Deep network as memory space: complexity, generalization, disentangled representation and interpretability
This work addresses the interpretability problem in deep learning for researchers and practitioners, offering a foundational but theoretical perspective without incremental improvements.
The authors tackled the interpretability of deep learning systems by proposing a geometrization framework that views deep networks as memory spaces, linking network complexity, generalization, and disentanglement to memory properties.
By bridging deep networks and physics, the programme of geometrization of deep networks was proposed as a framework for the interpretability of deep learning systems. Following this programme we can apply two key ideas of physics, the geometrization of physics and the least action principle, on deep networks and deliver a new picture of deep networks: deep networks as memory space of information, where the capacity, robustness and efficiency of the memory are closely related with the complexity, generalization and disentanglement of deep networks. The key components of this understanding include:(1) a Fisher metric based formulation of the network complexity; (2)the least action (complexity=action) principle on deep networks and (3)the geometry built on deep network configurations. We will show how this picture will bring us a new understanding of the interpretability of deep learning systems.