The SVD of Convolutional Weights: A CNN Interpretability Framework

by   Brenda Praggastis, et al.

Deep neural networks used for image classification often use convolutional filters to extract distinguishing features before passing them to a linear classifier. Most interpretability literature focuses on providing semantic meaning to convolutional filters to explain a model's reasoning process and confirm its use of relevant information from the input domain. Fully connected layers can be studied by decomposing their weight matrices using a singular value decomposition, in effect studying the correlations between the rows in each matrix to discover the dynamics of the map. In this work we define a singular value decomposition for the weight tensor of a convolutional layer, which provides an analogous understanding of the correlations between filters, exposing the dynamics of the convolutional map. We validate our definition using recent results in random matrix theory. By applying the decomposition across the linear layers of an image classification network we suggest a framework against which interpretability methods might be applied using hypergraphs to model class separation. Rather than looking to the activations to explain the network, we use the singular vectors with the greatest corresponding singular values for each linear layer to identify those features most important to the network. We illustrate our approach with examples and introduce the DeepDataProfiler library, the analysis tool used for this study.


page 13

page 18


Singular Value Decomposition and Neural Networks

Singular Value Decomposition (SVD) constitutes a bridge between the line...

The Local Dimension of Deep Manifold

Based on our observation that there exists a dramatic drop for the singu...

Boundary between noise and information applied to filtering neural network weight matrices

Deep neural networks have been successfully applied to a broad range of ...

Tubal Matrix Analysis

One of the early ideas started from the 2004 workshop is to regard third...

Improving training of deep neural networks via Singular Value Bounding

Deep learning methods achieve great success recently on many computer vi...

Image classification using local tensor singular value decompositions

From linear classifiers to neural networks, image classification has bee...

Emergence of the SVD as an interpretable factorization in deep learning for inverse problems

We demonstrate the emergence of weight matrix singular value decompositi...

Please sign up or login with your details

Forgot password? Click here to reset