中文
相关论文

相关论文: The Impact of Concept Explanations and Interventio…

200 篇论文

Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most…

计算机视觉与模式识别 · 计算机科学 2025-09-25 Nuoye Xiong , Anqi Dong , Ning Wang , Cong Hua , Guangming Zhu , Lin Mei , Peiyi Shen , Liang Zhang

Concept bottleneck models (CBMs) are a class of interpretable neural network models that predict the target response of a given input based on its high-level concepts. Unlike the standard end-to-end models, CBMs enable domain experts to…

机器学习 · 计算机科学 2023-07-04 Sungbin Shin , Yohan Jo , Sungsoo Ahn , Namhoon Lee

Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output. In this work, we…

机器学习 · 计算机科学 2024-10-29 Sonia Laguna , Ričards Marcinkevičs , Moritz Vandenhirtz , Julia E. Vogt

The lack of transparency in the decision-making processes of deep learning systems presents a significant challenge in modern artificial intelligence (AI), as it impairs users' ability to rely on and verify these systems. To address this…

Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Crucially, the CBM design inherently allows for human interventions, in which expert users are given…

机器学习 · 计算机科学 2024-08-07 Nishad Singhi , Jae Myung Kim , Karsten Roth , Zeynep Akata

There has been considerable recent interest in interpretable concept-based models such as Concept Bottleneck Models (CBMs), which first predict human-interpretable concepts and then map them to output classes. To reduce reliance on…

机器学习 · 计算机科学 2024-07-08 Simon Schrodi , Julian Schur , Max Argus , Thomas Brox

The design of interpretable deep learning models working in relational domains poses an open challenge: interpretable deep learning methods, such as Concept Bottleneck Models (CBMs), are not designed to solve relational problems, while…

Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final output. However, existing CBMs struggle to verify whether predicted concepts correspond to…

机器学习 · 计算机科学 2026-05-15 Yingying Fang , Haijie Xu , Shuang Wu , Mariathasan Anish , Guang Yang

Concept Bottleneck Models (CBMs) provide inherent interpretability by first predicting a set of human-understandable concepts and then mapping them to labels through a simple classifier. While users can intervene in the concept space to…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Hangzhou He , Lei Zhu , Kaiwen Li , Xinliang Zhang , Jiakui Hu , Ourui Fu , Zhengjian Yao , Yanye Lu

Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions. We…

机器学习 · 计算机科学 2023-04-28 Kushal Chauhan , Rishabh Tiwari , Jan Freyberg , Pradeep Shenoy , Krishnamurthy Dvijotham

Concept Bottleneck Models (CBMs) are machine learning models that improve interpretability by grounding their predictions on human-understandable concepts, allowing for targeted interventions in their decision-making process. However, when…

Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users. Among these techniqes, Concept Bottleneck Models enhance the interpretability of neural networks by…

机器学习 · 计算机科学 2024-05-28 Gabriele Dominici , Pietro Barbiero , Francesco Giannini , Martin Gjoreski , Marc Langhenirich

Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive…

计算机视觉与模式识别 · 计算机科学 2025-07-03 Katharina Prasse , Patrick Knab , Sascha Marton , Christian Bartelt , Margret Keuper

Concept Bottleneck Models (CBMs) provide explicit interpretations for deep neural networks through concepts and allow intervention with concepts to adjust final predictions. Existing CBMs assume concepts are conditionally independent given…

机器学习 · 计算机科学 2026-05-04 Haotian Xu , Tsui-Wei Weng , Lam M. Nguyen , Tengfei Ma

Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human…

机器学习 · 计算机科学 2026-03-10 Antonio De Santis , Schrasing Tong , Marco Brambilla , Lalana Kagal

Concept bottleneck models (CBMs), which predict human-interpretable concepts (e.g., nucleus shapes in cell images) before predicting the final output (e.g., cell type), provide insights into the decision-making processes of the model.…

计算机视觉与模式识别 · 计算机科学 2024-07-10 Winnie Pang , Xueyi Ke , Satoshi Tsutsui , Bihan Wen

Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relationships and causal mechanisms, and their…

机器学习 · 计算机科学 2026-01-16 Reza M. Asiyabi , SEOSAW Partnership , Steven Hancock , Casey Ryan

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an…

Concept Bottleneck Models (CBMs) are neural networks designed to conjoin high performance with ante-hoc interpretability. CBMs work by first mapping inputs (e.g., images) to high-level concepts (e.g., visible objects and their properties)…

Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs) have emerged as a promising approach to mitigate this issue by learning…

机器学习 · 计算机科学 2026-01-30 Antonio Almudévar , José Miguel Hernández-Lobato , Alfonso Ortega
‹ 上一页 1 2 3 10 下一页 ›