paper-with-me

Papers

Understanding Regularization to Visualize Convolutional Neural Networks

2018-04-20 · Maximilian Baust, Florian Ludwig, Christian Rupprecht, Matthias Kohl, Stefan Braunewell

Variational methods for revealing visual concepts learned by convolutional neural networks have gained significant attention during the last years. Being based on noisy gradients obtained via back-propagation such methods require the application of regularization strategies. We present a mathematical framework unifying previously employed regularization methods. Within this framework, we propose a novel technique based on Sobolev gradients which can be implemented via convolutions and does not require specialized numerical treatment, such as total variation regularization. The experiments performed on feature inversion and activation maximization demonstrate the benefit of a unified approach to regularization, such as sharper reconstructions via the proposed Sobolev filters and a better control over reconstructed scales.

📄 PDF Abstract BibTeX arXiv:1805.00071

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Understanding Neural Networks Through Deep Visualization

2015-06-22 · Jason Yosinski, Jeff Clune, Anh Nguyen, Thomas Fuchs 외

Recent years have produced great advances in training large, deep neural networks (DNNs), including notable successes in training convolutional neural networks (convnets) to recognize natural images. However, our underst…

Interpretable Machine Learning

Feature Visualization in 3D Convolutional Neural Networks

2025-05-12 · Chunpeng Li, Ya-tang Li

Understanding the computations of convolutional neural networks requires effective visualization of their kernels. While maximal activation methods have proven successful in highlighting the preferred features of 2D conv…

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

2019-04-30 · Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard 외

Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships. To address this weakn…

Node ClassificationNode Classification on Non-Homophilic (Heterophilic) Graphs

Understanding Neural Network Systems for Image Analysis using Vector Spaces and Inverse Maps

2024-02-01 · Rebecca Pattichis, Marios S. Pattichis

There is strong interest in developing mathematical methods that can be used to understand complex neural networks used in image analysis. In this paper, we introduce techniques from Linear Algebra to model neural networ…

Interpreting intermediate convolutional layers in unsupervised acoustic word classification

2021-10-05 · Gašper Beguš, Alan Zhou

Understanding how deep convolutional neural networks classify data has been subject to extensive research. This paper proposes a technique to visualize and interpret intermediate layers of unsupervised deep convolutional…

ClassificationregressionTime SeriesTime Series Analysis