English
Related papers

Related papers: Disentangling Neuron Representations with Concept …

200 papers

Deep neural networks (DNNs) have demonstrated impressive performance on a wide array of tasks, but they are usually considered opaque since internal structure and learned parameters are not interpretable. In this paper, we re-examine the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-21 Yinpeng Dong , Hang Su , Jun Zhu , Fan Bao

Sentence embeddings are central to modern NLP and AI systems, yet little is known about their internal structure. While we can compare these embeddings using measures such as cosine similarity, the contributing features are not…

Computation and Language · Computer Science 2025-06-11 Matthieu Tehenan , Vikram Natarajan , Jonathan Michala , Milton Lin , Juri Opitz

It has long been speculated that deep neural networks function by discovering a hierarchical set of domain-specific core concepts or patterns, which are further combined to recognize even more elaborate concepts for the classification or…

Computation and Language · Computer Science 2019-07-25 Guntis Barzdins , Eduards Sidorovics

Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Tao Yang , Yuwang Wang , Yan Lu , Nanning Zheng

Word embeddings are rich word representations, which in combination with deep neural networks, lead to large performance gains for many NLP tasks. However, word embeddings are represented by dense, real-valued vectors and they are therefore…

Computation and Language · Computer Science 2019-12-24 Andreas Hanselowski , Iryna Gurevych

Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work…

Computer Vision and Pattern Recognition · Computer Science 2021-05-25 Sandareka Wickramanayake , Wynne Hsu , Mong Li Lee

Distributed representations of words have boosted the performance of many Natural Language Processing tasks. However, usually only one representation per word is obtained, not acknowledging the fact that some words have multiple meanings.…

Computation and Language · Computer Science 2016-02-22 Luis Nieto Piña , Richard Johansson

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

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

Mounting evidence in neuroscience suggests the possibility of neuronal representations that individual neurons serve as the substrates of different mental representations in a point-to-point way. Combined with associationism, it can…

Neurons and Cognition · Quantitative Biology 2021-09-06 Chiyin Zheng

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

The interpretation of deep neural networks (DNNs) has become a key topic as more and more people apply them to solve various problems and making critical decisions. Concept-based explanations have recently become a popular approach for…

Human-Computer Interaction · Computer Science 2021-08-10 Zhenge Zhao , Panpan Xu , Carlos Scheidegger , Liu Ren

We introduce a method that takes advantage of high-quality pretrained multimodal representations to explore fine-grained semantic networks in the human brain. Previous studies have documented evidence of functional localization in the…

Artificial Intelligence · Computer Science 2023-06-07 Cory Efird , Alex Murphy , Joel Zylberberg , Alona Fyshe

Neural networks often contain polysemantic neurons that respond to multiple, sometimes unrelated, features, complicating mechanistic interpretability. We introduce the Polysemanticity Index (PSI), a null-calibrated metric that quantifies…

Machine Learning · Computer Science 2025-08-26 Manan Gupta , Dhruv Kumar

By highlighting the regions of the input image that contribute the most to the decision, saliency maps have become a popular method to make neural networks interpretable. In medical imaging, they are particularly well-suited to explain…

Computer Vision and Pattern Recognition · Computer Science 2023-01-06 Kaifeng Zou , Sylvain Faisan , Fabrice Heitz , Marie Epain , Pierre Croisille , Laurent Fanton , Sébastien Valette

The mathematical representation of semantics is a key issue for Natural Language Processing (NLP). A lot of research has been devoted to finding ways of representing the semantics of individual words in vector spaces. Distributional…

Computation and Language · Computer Science 2014-11-13 Karl Moritz Hermann

We address the key question of how object part representations can be found from the internal states of CNNs that are trained for high-level tasks, such as object classification. This work provides a new unsupervised method to learn…

Machine Learning · Computer Science 2016-11-15 Jianyu Wang , Zhishuai Zhang , Cihang Xie , Vittal Premachandran , Alan Yuille

Multimodal Emotion Recognition refers to the classification of input video sequences into emotion labels based on multiple input modalities (usually video, audio and text). In recent years, Deep Neural networks have shown remarkable…

Machine Learning · Computer Science 2024-10-28 Ashish Ramayee Asokan , Nidarshan Kumar , Anirudh Venkata Ragam , Shylaja S Sharath

Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble human semantic…

Computation and Language · Computer Science 2018-11-15 Steven Derby , Paul Miller , Brian Murphy , Barry Devereux

A creative idea is often born from transforming, combining, and modifying ideas from existing visual examples capturing various concepts. However, one cannot simply copy the concept as a whole, and inspiration is achieved by examining…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Yael Vinker , Andrey Voynov , Daniel Cohen-Or , Ariel Shamir