Activation Landscapes as a Topological Summary of Neural Network Performance

Abstract

We use topological data analysis (TDA) to study how data transforms as it passes through successive layers of a deep neural network (DNN). We compute the persistent homology of the activation data for each layer of the network and summarize this information using persistence landscapes. The resulting feature map provides both an informative visual- ization of the network and a kernel for statistical analysis and machine learning. We observe that the topological complexity often increases with training and that the topological complexity does not decrease with each layer.

4 pages, 5 figures

References in corpus (6)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Understanding Neural Networks Through Deep Visualization
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks
• Connectivity-Optimized Representation Learning via Persistent Homology
• Applying Topological Persistence in Convolutional Neural Network for Music Audio Signals

Cited by in corpus (1)

• Topology-Aware Activation Functions in Neural Networks