The SVD of Convolutional Weights: A CNN Interpretability Framework

• URL: http://arxiv.org/abs/2208.06894v1
• Date: Sun, 14 Aug 2022 18:23:02 GMT
• Title: The SVD of Convolutional Weights: A CNN Interpretability Framework
• Authors: Brenda Praggastis, Davis Brown, Carlos Ortiz Marrero, Emilie Purvine, Madelyn Shapiro, and Bei Wang
• Abstract summary: We propose 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.
• Score: 3.5783190448496343
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Linking in Style: Understanding learned features in deep learning models [0.0]
  Convolutional neural networks (CNNs) learn abstract features to perform object classification. We propose an automatic method to visualize and systematically analyze learned features in CNNs.
  arXiv  Detail & Related papers  (2024-09-25T12:28:48Z)
• Classification of Buried Objects from Ground Penetrating Radar Images by using Second Order Deep Learning Models [3.332733725674752]
  A new classification model based on covariance matrices is built in order to classify buried objects. We show in a large database that our approach outperform shallow networks designed for GPR data. We also illustrate the interest of our models when training data and test sets are obtained from different weather modes or considerations.
  arXiv  Detail & Related papers  (2024-09-20T08:42:30Z)
• A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features [54.83898311047626]
  We consider neural networks with piecewise linear activations ranging from 2 to an arbitrary but finite number of layers. We first show that two-layer networks with piecewise linear activations are Lasso models using a discrete dictionary of ramp depths.
  arXiv  Detail & Related papers  (2024-03-02T00:33:45Z)
• Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations [15.59251297818324]
  We present an approach for analyzing grouping information contained within a neural network's activations. We exploit features from all layers and obviating the need to guess which part of the model contains relevant information.
  arXiv  Detail & Related papers  (2023-12-11T01:20:34Z)
• Hodge-Aware Contrastive Learning [101.56637264703058]
  Simplicial complexes prove effective in modeling data with multiway dependencies. We develop a contrastive self-supervised learning approach for processing simplicial data.
  arXiv  Detail & Related papers  (2023-09-14T00:40:07Z)
• Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers [0.0]
  We investigate the impact on deep network performances of a training approach. We propose a neural network architecture which induces an error function involving the outputs of all the network layers.
  arXiv  Detail & Related papers  (2023-06-09T10:52:49Z)
• Extracting Semantic Knowledge from GANs with Unsupervised Learning [65.32631025780631]
  Generative Adversarial Networks (GANs) encode semantics in feature maps in a linearly separable form. We propose a novel clustering algorithm, named KLiSH, which leverages the linear separability to cluster GAN's features. KLiSH succeeds in extracting fine-grained semantics of GANs trained on datasets of various objects.
  arXiv  Detail & Related papers  (2022-11-30T03:18:16Z)
• Graph Polynomial Convolution Models for Node Classification of Non-Homophilous Graphs [52.52570805621925]
  We investigate efficient learning from higher-order graph convolution and learning directly from adjacency matrix for node classification. We show that the resulting model lead to new graphs and residual scaling parameter. We demonstrate that the proposed methods obtain improved accuracy for node-classification of non-homophilous parameters.
  arXiv  Detail & Related papers  (2022-09-12T04:46:55Z)
• Graph Kernel Neural Networks [53.91024360329517]
  We propose to use graph kernels, i.e. kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type of graph kernels and has the added benefit of providing some interpretability.
  arXiv  Detail & Related papers  (2021-12-14T14:48:08Z)
• Interpreting intermediate convolutional layers in unsupervised acoustic word classification [0.0]
  This paper proposes a technique to visualize and interpret intermediate layers of unsupervised deep convolutional neural networks. A GAN-based architecture (ciwGAN arXiv:2006.02951) was trained on unlabeled sliced lexical items from TIMIT.
  arXiv  Detail & Related papers  (2021-10-05T21:53:32Z)
• Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems [107.3868459697569]
  We introduce an eigendecomposition-free approach to training a deep network. We show that our approach is much more robust than explicit differentiation of the eigendecomposition. Our method has better convergence properties and yields state-of-the-art results.
  arXiv  Detail & Related papers  (2020-04-15T04:29:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.