Ayasdi: Using Topological Data Analysis to Understand Behavior of Convolutional Neural Networks

TLDR: Neural Networks are powerful but complex and opaque tools. Using Topological Data Analysis, we can describe the functioning and learning of a convolutional neural network in a compact and understandable way. The implications of the findings are profound and will accelerate the development of a wide range of applications from self-driving cars and drones to complying with things like GDPR.

Introduction
Neural networks have demonstrated a great deal of success in the study of various