English
Related papers

Related papers: On Spectral Properties of Gradient-based Explanati…

200 papers

Binarized Neural Networks (BNNs) have the potential to revolutionize the way that deep learning is carried out in edge computing platforms. However, the effectiveness of interpretability methods on these networks has not been assessed. In…

Computer Vision and Pattern Recognition · Computer Science 2021-06-24 Amy Widdicombe , Simon J. Julier

Gradients play a pivotal role in neural networks explanation. The inherent high dimensionality and structural complexity of neural networks result in the original gradients containing a significant amount of noise. While several approaches…

Machine Learning · Computer Science 2024-07-02 Linjiang Zhou , Xiaochuan Shi , Chao Ma , Zepeng Wang

Spectral methods have emerged as a simple yet surprisingly effective approach for extracting information from massive, noisy and incomplete data. In a nutshell, spectral methods refer to a collection of algorithms built upon the eigenvalues…

Machine Learning · Statistics 2021-10-26 Yuxin Chen , Yuejie Chi , Jianqing Fan , Cong Ma

This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Felipe Torres Figueroa , Hanwei Zhang , Ronan Sicre , Yannis Avrithis , Stephane Ayache

When do gradient-based explanation algorithms provide perceptually-aligned explanations? We propose a criterion: the feature attributions need to be aligned with the tangent space of the data manifold. To provide evidence for this…

Machine Learning · Computer Science 2024-07-16 Sebastian Bordt , Uddeshya Upadhyay , Zeynep Akata , Ulrike von Luxburg

Graph neural networks (GNNs) are quickly becoming the standard approach for learning on graph structured data across several domains, but they lack transparency in their decision-making. Several perturbation-based approaches have been…

Machine Learning · Computer Science 2021-11-29 Anna Himmelhuber , Mitchell Joblin , Martin Ringsquandl , Thomas Runkler

Explanation methods help understand the reasons for a model's prediction. These methods are increasingly involved in model debugging, performance optimization, and gaining insights into the workings of a model. With such critical…

Machine Learning · Computer Science 2025-04-16 Mihir Mulye , Matias Valdenegro-Toro

Interpretability methods for deep neural networks mainly focus on the sensitivity of the class score with respect to the original or perturbed input, usually measured using actual or modified gradients. Some methods also use a…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Md Mahfuzur Rahman , Noah Lewis , Sergey Plis

Deep learning interpretation is essential to explain the reasoning behind model predictions. Understanding the robustness of interpretation methods is important especially in sensitive domains such as medical applications since…

Machine Learning · Computer Science 2019-10-21 Alexander Levine , Sahil Singla , Soheil Feizi

In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc visual explanations for neural networks. Predictive uncertainty refers to the variability in the network predictions under perturbations to the…

Machine Learning · Computer Science 2024-06-04 Mohit Prabhushankar , Ghassan AlRegib

Misinformation is still a major societal problem and the arrival of Large Language Models (LLMs) only added to it. This paper analyzes synthetic, false, and genuine information in the form of text from spectral analysis, visualization, and…

Artificial Intelligence · Computer Science 2024-07-09 Vishnu S. Pendyala , Madhulika Dutta

Classification models are expected to perform equally well for different classes, yet in practice, there are often large gaps in their performance. This issue of class bias is widely studied in cases of datasets with sample imbalance, but…

Machine Learning · Computer Science 2024-06-04 Chiraag Kaushik , Ran Liu , Chi-Heng Lin , Amrit Khera , Matthew Y Jin , Wenrui Ma , Vidya Muthukumar , Eva L Dyer

Post-hoc explanation methods are used with the intent of providing insights about neural networks and are sometimes said to help engender trust in their outputs. However, popular explanations methods have been found to be fragile to minor…

Machine Learning · Computer Science 2022-12-19 Matthew Wicker , Juyeon Heo , Luca Costabello , Adrian Weller

Deep learning is currently the subject of intensive study. However, fundamental concepts such as representations are not formally defined -- researchers "know them when they see them" -- and there is no common language for describing and…

Machine Learning · Computer Science 2015-09-30 David Balduzzi

Several methods have been proposed to explain Deep Neural Network (DNN). However, to our knowledge, only classification networks have been studied to try to determine which input dimensions motivated the decision. Furthermore, as there is…

Computer Vision and Pattern Recognition · Computer Science 2020-04-16 Mégane Millan , Catherine Achard

Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Ali Karkehabadi , Jamshid Hassanpour , Houman Homayoun , Avesta Sasan

In Hezaveh et al. 2017 we showed that deep learning can be used for model parameter estimation and trained convolutional neural networks to determine the parameters of strong gravitational lensing systems. Here we demonstrate a method for…

Cosmology and Nongalactic Astrophysics · Physics 2017-11-29 Laurence Perreault Levasseur , Yashar D. Hezaveh , Risa H. Wechsler

Most successful machine intelligence systems rely on gradient-based learning, which is made possible by backpropagation. Some systems are designed to aid us in interpreting data when explicit goals cannot be provided. These unsupervised…

Machine Learning · Computer Science 2018-06-05 Aditya Ramesh , Yann LeCun

The problem of attribution is concerned with identifying the parts of an input that are responsible for a model's output. An important family of attribution methods is based on measuring the effect of perturbations applied to the input. In…

Computer Vision and Pattern Recognition · Computer Science 2019-10-21 Ruth Fong , Mandela Patrick , Andrea Vedaldi

As Large Language Models (LLMs) are increasingly integrated in diverse applications, obtaining reliable measures of their predictive uncertainty has become critically important. A precise distinction between aleatoric uncertainty, arising…