English
Related papers

Related papers: Concept-based Explanations using Non-negative Conc…

200 papers

In image classification, Convolutional Neural Network(CNN) models have achieved high performance with the rapid development in deep learning. However, some categories in the image datasets are more difficult to distinguished than others.…

Computer Vision and Pattern Recognition · Computer Science 2019-06-05 Yuntao Liu , Yong Dou , Ruochun Jin , Peng Qiao

Convolutional neural networks (CNNs) are increasingly being used in critical systems, where robustness and alignment are crucial. In this context, the field of explainable artificial intelligence has proposed the generation of high-level…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Andres Felipe Posada-Moreno , Nikita Surya , Sebastian Trimpe

Interpretability research often adopts a neuron-centric lens, treating individual neurons as the fundamental units of explanation. However, neuron-level explanations can be undermined by superposition, where single units respond to mixtures…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Julien Colin , Lore Goetschalckx , Thomas Fel , Victor Boutin , Thomas Serre , Nuria Oliver

With the advent of highly predictive but opaque deep learning models, it has become more important than ever to understand and explain the predictions of such models. Existing approaches define interpretability as the inverse of complexity…

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…

Computation and Language · Computer Science 2018-08-30 Haoyue Shi , Hao Zhou , Jiaze Chen , Lei Li

A variety of methods exist to explain image classification models. However, whether they provide any benefit to users over simply comparing various inputs and the model's respective predictions remains unclear. We conducted a user study…

Machine Learning · Computer Science 2022-04-26 Leon Sixt , Martin Schuessler , Oana-Iuliana Popescu , Philipp Weiß , Tim Landgraf

This paper presents a method to explain the knowledge encoded in a convolutional neural network (CNN) quantitatively and semantically. The analysis of the specific rationale of each prediction made by the CNN presents a key issue of…

Computer Vision and Pattern Recognition · Computer Science 2018-12-19 Runjin Chen , Hao Chen , Ge Huang , Jie Ren , Quanshi Zhang

Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature…

Machine Learning · Statistics 2019-10-09 Amirata Ghorbani , James Wexler , James Zou , Been Kim

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…

Machine Learning · Computer Science 2018-03-14 Osbert Bastani , Carolyn Kim , Hamsa Bastani

Can a deep neural network be approximated by a small decision tree based on simple features? This question and its variants are behind the growing demand for machine learning models that are *interpretable* by humans. In this work we study…

Machine Learning · Computer Science 2024-06-18 Marco Bressan , Nicolò Cesa-Bianchi , Emmanuel Esposito , Yishay Mansour , Shay Moran , Maximilian Thiessen

We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automatically finds visual…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Neehar Kondapaneni , Markus Marks , Oisin Mac Aodha , Pietro Perona

This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance…

Computer Vision and Pattern Recognition · Computer Science 2018-02-08 Quanshi Zhang , Song-Chun Zhu

Convolutional neural networks (CNN) are known for their excellent feature extraction capabilities to enable the learning of models from data, yet are used as black boxes. An interpretation of the convolutional filtres and associated…

Machine Learning · Computer Science 2022-07-27 Shagufta Henna , Juan Miguel Lopez Alcaraz

In many scenarios, human decisions are explained based on some high-level concepts. In this work, we take a step in the interpretability of neural networks by examining their internal representation or neuron's activations against concepts.…

Machine Learning · Computer Science 2021-11-09 Mohammad Nokhbeh Zaeem , Majid Komeili

Safety-critical applications require transparency in artificial intelligence (AI) components, but widely used convolutional neural networks (CNNs) widely used for perception tasks lack inherent interpretability. Hence, insights into what…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 Georgii Mikriukov , Gesina Schwalbe , Christian Hellert , Korinna Bade

Concept-based explainability methods provide insight into deep learning systems by constructing explanations using human-understandable concepts. While the literature on human reasoning demonstrates that we exploit relationships between…

Machine Learning · Computer Science 2024-05-29 Naveen Raman , Mateo Espinosa Zarlenga , Mateja Jamnik

In spite of several claims stating that some models are more interpretable than others -- e.g., "linear models are more interpretable than deep neural networks" -- we still lack a principled notion of interpretability to formally compare…

Artificial Intelligence · Computer Science 2020-11-16 Pablo Barceló , Mikaël Monet , Jorge Pérez , Bernardo Subercaseaux

Concept-based interpretations of black-box models are often more intuitive for humans to understand. The most widely adopted approach for concept-based interpretation is Concept Activation Vector (CAV). CAV relies on learning a linear…

Machine Learning · Computer Science 2024-02-07 Andrew Bai , Chih-Kuan Yeh , Pradeep Ravikumar , Neil Y. C. Lin , Cho-Jui Hsieh

Concept-based explanations translate the internal representations of deep learning models into a language that humans are familiar with: concepts. One popular method for finding concepts is Concept Activation Vectors (CAVs), which are…

Machine Learning · Computer Science 2025-02-14 Angus Nicolson , Lisa Schut , J. Alison Noble , Yarin Gal

While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…

Machine Learning · Computer Science 2025-07-09 Sofiia Chorna , Kateryna Tarelkina , Eloïse Berthier , Gianni Franchi