Experimental Observations of the Topology of Convolutional Neural Network Activations

by   Emilie Purvine, et al.

Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture, resulting in high-dimensional, difficult-to-interpret internal representations of input data. As DNNs become more ubiquitous across multiple sectors of our society, there is increasing recognition that mathematical methods are needed to aid analysts, researchers, and practitioners in understanding and interpreting how these models' internal representations relate to the final classification. In this paper, we apply cutting edge techniques from TDA with the goal of gaining insight into the interpretability of convolutional neural networks used for image classification. We use two common TDA approaches to explore several methods for modeling hidden-layer activations as high-dimensional point clouds, and provide experimental evidence that these point clouds capture valuable structural information about the model's process. First, we demonstrate that a distance metric based on persistent homology can be used to quantify meaningful differences between layers, and we discuss these distances in the broader context of existing representational similarity metrics for neural network interpretability. Second, we show that a mapper graph can provide semantic insight into how these models organize hierarchical class knowledge at each layer. These observations demonstrate that TDA is a useful tool to help deep learning practitioners unlock the hidden structures of their models.


page 4

page 5

page 6

page 7

page 10


New Perspective of Interpretability of Deep Neural Networks

Deep neural networks (DNNs) are known as black-box models. In other word...

Adaptive Topological Feature via Persistent Homology: Filtration Learning for Point Clouds

Machine learning for point clouds has been attracting much attention, wi...

Geometric and Topological Inference for Deep Representations of Complex Networks

Understanding the deep representations of complex networks is an importa...

PCEDNet : A Neural Network for Fast and Efficient Edge Detection in 3D Point Clouds

In recent years, Convolutional Neural Networks (CNN) have proven to be e...

Representation Topology Divergence: A Method for Comparing Neural Network Representations

Comparison of data representations is a complex multi-aspect problem tha...

A Detailed Study of Interpretability of Deep Neural Network based Top Taggers

Recent developments in the methods of explainable AI (xAI) methods allow...

Understanding Neural Networks Through Deep Visualization

Recent years have produced great advances in training large, deep neural...

Please sign up or login with your details

Forgot password? Click here to reset