English
Related papers

Related papers: Utilizing Mutations to Evaluate Interpretability o…

200 papers

Deep convolutional neural networks have proven their effectiveness, and have been acknowledged as the most dominant method for image classification. However, a severe drawback of deep convolutional neural networks is poor explainability.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Bin Wang , Wenbin Pei , Bing Xue , Mengjie Zhang

A number of backpropagation-based approaches such as DeConvNets, vanilla Gradient Visualization and Guided Backpropagation have been proposed to better understand individual decisions of deep convolutional neural networks. The saliency maps…

Computer Vision and Pattern Recognition · Computer Science 2019-09-04 Jindong Gu , Yinchong Yang , Volker Tresp

Understanding decisions made by neural networks is key for the deployment of intelligent systems in real world applications. However, the opaque decision making process of these systems is a disadvantage where interpretability is essential.…

Machine Learning · Computer Science 2023-04-12 Kai Fischer , Jonas Schneider

Model pruning technique is vital for accelerating large language models by reducing their size and computational requirements. However, the generalizability of existing pruning methods across diverse datasets and tasks remains unclear.…

Computation and Language · Computer Science 2025-03-04 Yizhuo Ding , Xinwei Sun , Yanwei Fu , Guosheng Hu

A framework is presented to extract and understand decision-making information from a deep neural network (DNN) classifier of jet substructure tagging techniques. The general method studied is to provide expert variables that augment inputs…

Data Analysis, Statistics and Probability · Physics 2023-01-11 Garvita Agarwal , Lauren Hay , Ia Iashvili , Benjamin Mannix , Christine McLean , Margaret Morris , Salvatore Rappoccio , Ulrich Schubert

Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution techniques struggle to operate at neuron level. In this paper,…

Computation and Language · Computer Science 2024-09-26 Zeping Yu , Sophia Ananiadou

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose…

Computer Vision and Pattern Recognition · Computer Science 2017-03-31 Yinpeng Dong , Hang Su , Jun Zhu , Bo Zhang

Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevant each feature is for the prediction of a deep neural…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Robin Hesse , Simone Schaub-Meyer , Stefan Roth

Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score using modified rules, rather than the gradient. We analyze…

Machine Learning · Computer Science 2024-02-20 Leon Sixt , Maximilian Granz , Tim Landgraf

Machine learning methods are solving very successfully a plethora of tasks, but they have the disadvantage of not providing any information about their decision. Consequently, estimating the reasoning of the system provides additional…

Machine Learning · Computer Science 2025-01-27 Eric Nyiri , Olivier Gibaru

While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the variety of tasks to be solved. In this chapter, we explore…

Machine learning (ML) model explainability has received growing attention, especially in the area related to model risk and regulations. In this paper, we reviewed and compared some popular ML model explainability methodologies, especially…

Artificial Intelligence · Computer Science 2021-06-15 Shafie Gholizadeh , Nengfeng Zhou

Deep neural networks have led to state-of-the-art results in many medical imaging tasks including Alzheimer's disease (AD) detection based on structural magnetic resonance imaging (MRI) data. However, the network decisions are often…

Quantitative Methods · Quantitative Biology 2019-08-28 Moritz Böhle , Fabian Eitel , Martin Weygandt , Kerstin Ritter

The limited transparency of the inner decision-making mechanism in deep neural networks (DNN) and other machine learning (ML) models has hindered their application in several domains. In order to tackle this issue, feature attribution…

Machine Learning · Computer Science 2023-10-30 Dong Qin , George Amariucai , Daji Qiao , Yong Guan , Shen Fu

To solve the problem that convolutional neural networks (CNNs) are difficult to process non-grid type relational data like graphs, Kipf et al. proposed a graph convolutional neural network (GCN). The core idea of the GCN is to perform…

Machine Learning · Computer Science 2019-04-17 Shangsheng Xie , Mingming Lu

In Neural Machine Translation (and, more generally, conditional language modeling), the generation of a target token is influenced by two types of context: the source and the prefix of the target sequence. While many attempts to understand…

Computation and Language · Computer Science 2021-06-28 Elena Voita , Rico Sennrich , Ivan Titov

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…

Computation and Language · Computer Science 2021-09-06 Paul Michel

Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they…

Computer Vision and Pattern Recognition · Computer Science 2019-08-14 Moustafa Alzantot , Amy Widdicombe , Simon Julier , Mani Srivastava

This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DNNs, we may easily collect hundreds of checkpoints from…

Machine Learning · Computer Science 2022-08-31 Yandong Li , Xuhui Jia , Ruoxin Sang , Yukun Zhu , Bradley Green , Liqiang Wang , Boqing Gong

Training data attribution (TDA) methods aim to identify which training examples influence a model's predictions on specific test data most. By quantifying these influences, TDA supports critical applications such as data debugging,…

Machine Learning · Computer Science 2025-05-30 Xingyuan Pan , Chenlu Ye , Joseph Melkonian , Jiaqi W. Ma , Tong Zhang