English
Related papers

Related papers: Information-Theoretic Visual Explanation for Black…

200 papers

Neural networks are ubiquitous in applied machine learning for education. Their pervasive success in predictive performance comes alongside a severe weakness, the lack of explainability of their decisions, especially relevant in…

Machine Learning · Computer Science 2022-07-04 Vinitra Swamy , Bahar Radmehr , Natasa Krco , Mirko Marras , Tanja Käser

Large Language Models (LLMs) excel on many task-specific benchmarks, yet the mechanisms that drive this success remain poorly understood. We move from asking what these systems can do to asking how they process information. Our contribution…

Artificial Intelligence · Computer Science 2026-02-04 Jae Wan Shim

Methods for interpreting machine learning black-box models increase the outcomes' transparency and in turn generates insight into the reliability and fairness of the algorithms. However, the interpretations themselves could contain…

Machine Learning · Computer Science 2019-06-05 Yujia Zhang , Kuangyan Song , Yiming Sun , Sarah Tan , Madeleine Udell

We consider the problem of evaluating black-box multi-class classifiers. In the standard setup, we observe class labels $Y\in \{0,1,\ldots,M-1\}$ generated according to the conditional distribution $ Y|X \sim \text{…

Methodology · Statistics 2026-04-08 Yuchen Chen , Jing Lei

The field of Explainable Artificial Intelligence (XAI) aims to improve the interpretability of black-box machine learning models. Building a heatmap based on the importance value of input features is a popular method for explaining the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Amirhossein Aminimehr , Pouya Khani , Amirali Molaei , Amirmohammad Kazemeini , Erik Cambria

In designing an intelligent system that must be able to explain its reasoning to a human user, or to provide generalizations that the human user finds reasonable, it may be useful to take into consideration psychological data on what types…

Artificial Intelligence · Computer Science 2013-04-15 James E. Corter , Mark A. Gluck

Feature attribution methods are widely used for explaining image-based predictions, as they provide feature-level insights that can be intuitively visualized. However, such explanations often vary in their robustness and may fail to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Amr Alkhatib , Stephanie Lowry

Multi-instance learning (MIL) has a wide range of applications due to its distinctive characteristics. Although many state-of-the-art algorithms have achieved decent performances, a plurality of existing methods solve the problem only in…

Machine Learning · Statistics 2015-12-04 Hanqiang Song , Zhuotun Zhu , Xinggang Wang

The need for transparency of predictive systems based on Machine Learning algorithms arises as a consequence of their ever-increasing proliferation in the industry. Whenever black-box algorithmic predictions influence human affairs, the…

Machine Learning · Computer Science 2020-02-11 Kacper Sokol , Peter Flach

Classification is a major tool of statistics and machine learning. A classification method first processes a training set of objects with given classes (labels), with the goal of afterward assigning new objects to one of these classes. When…

Machine Learning · Statistics 2024-07-08 Jakob Raymaekers , Peter J. Rousseeuw , Mia Hubert

The purported "black box" nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of…

Computer Vision and Pattern Recognition · Computer Science 2019-10-15 Avanti Shrikumar , Peyton Greenside , Anshul Kundaje

Interpretable machine learning seeks to understand the reasoning process of complex black-box systems that are long notorious for lack of explainability. One flourishing approach is through counterfactual explanations, which provide…

Artificial Intelligence · Computer Science 2023-06-02 Vy Vo , Trung Le , Van Nguyen , He Zhao , Edwin Bonilla , Gholamreza Haffari , Dinh Phung

The ability of to explain neural network decisions goes hand in hand with their safe deployment. Several methods have been proposed to highlight features important for a given network decision. However, there is no consensus on how to…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Agnieszka Grabska-Barwińska

Integrated Information Theory (IIT) is a prominent theory of consciousness that has at its centre measures that quantify the extent to which a system generates more information than the sum of its parts. While several candidate measures of…

Neurons and Cognition · Quantitative Biology 2019-01-30 Pedro A. M. Mediano , Anil K. Seth , Adam B. Barrett

Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…

Artificial Intelligence · Computer Science 2020-07-21 Teodora Popordanoska , Mohit Kumar , Stefano Teso

Understanding how a complex machine learning model makes a classification decision is essential for its acceptance in sensitive areas such as health care. Towards this end, we present PatchNet, a method that provides the features indicative…

Computer Vision and Pattern Recognition · Computer Science 2018-12-03 Adityanarayanan Radhakrishnan , Charles Durham , Ali Soylemezoglu , Caroline Uhler

The development of AI-based methods to analyze radiology reports could lead to significant advances in medical diagnosis, from improving diagnostic accuracy to enhancing efficiency and reducing workload. However, the lack of…

Computation and Language · Computer Science 2025-08-14 Yuyan Ge , Kwan Ho Ryan Chan , Pablo Messina , René Vidal

We consider the problem of classification with a (peer-to-peer) network of heterogeneous and partially informative agents, each receiving local data generated by an underlying true class, and equipped with a classifier that can only…

Machine Learning · Computer Science 2024-10-01 Tong Yao , Shreyas Sundaram

We study the problem of large scale, multi-label visual recognition with a large number of possible classes. We propose a method for augmenting a trained neural network classifier with auxiliary capacity in a manner designed to…

Machine Learning · Statistics 2015-04-15 David Warde-Farley , Andrew Rabinovich , Dragomir Anguelov

Co-occurrent visual pattern makes aggregating contextual information a common paradigm to enhance the pixel representation for semantic image segmentation. The existing approaches focus on modeling the context from the perspective of the…

Computer Vision and Pattern Recognition · Computer Science 2021-08-30 Zhenchao Jin , Bin Liu , Qi Chu , Nenghai Yu