GTC Silicon Valley-2019 ID:S9287:Understanding Deep Networks through Properties of the Input Space
Sebastian Palacio(German Research Center for Artificial Intelligence (DFKI))
We'll explore how to discover properties of deep networks by looking at their learned parameters or measuring the patterns of the networks' input space. Emerging properties from individual samples can be measured by examining the common changes they undergo during training. We'll explain how this allows a hierarchical analysis that goes beyond explainability of individual decisions why a particular image was misclassified, for example and extends to entire classes or even the training dataset itself. We show how understanding these patterns can provide the foundation for more principled, stable, and robust definitions of future network architectures and more consistent learning procedures.