English
Related papers

Related papers: CoSy: Evaluating Textual Explanations of Neurons

200 papers

Neuro-Symbolic (NeSy) integration combines symbolic reasoning with Neural Networks (NNs) for tasks requiring perception and reasoning. Most NeSy systems rely on continuous relaxation of logical knowledge, and no discrete decisions are made…

Machine Learning · Computer Science 2024-02-28 Alessandro Daniele , Tommaso Campari , Sagar Malhotra , Luciano Serafini

Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its…

Machine Learning · Computer Science 2024-10-07 Hamed Behzadi-Khormouji , José Oramas

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

Mechanistic interpretability aims to understand how models store representations by breaking down neural networks into interpretable units. However, the occurrence of polysemantic neurons, or neurons that respond to multiple unrelated…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Laura O'Mahony , Vincent Andrearczyk , Henning Muller , Mara Graziani

We propose a neuropsychological approach to the explainability of artificial neural networks, which involves using concepts from human cognitive psychology as relevant heuristic references for developing synthetic explanatory frameworks…

In this paper, convolutional layers of pre-trained VGG16 model are analyzed. The analysis is based on the responses of neurons to the images of classes in ImageNet database. First, a visualization method is proposed in order to illustrate…

Computer Vision and Pattern Recognition · Computer Science 2020-07-02 Zahra Sadeghi

Neuron Interpretation has gained traction in the field of interpretability, and have provided fine-grained insights into what a model learns and how language knowledge is distributed amongst its different components. However, the lack of…

Computation and Language · Computer Science 2023-11-07 Yimin Fan , Fahim Dalvi , Nadir Durrani , Hassan Sajjad

Human explanations of high-level decisions are often expressed in terms of key concepts the decisions are based on. In this paper, we study such concept-based explainability for Deep Neural Networks (DNNs). First, we define the notion of…

Machine Learning · Computer Science 2022-02-09 Chih-Kuan Yeh , Been Kim , Sercan O. Arik , Chun-Liang Li , Tomas Pfister , Pradeep Ravikumar

It is essential for understanding neural network decisions to interpret the functionality (also known as concepts) of neurons. Existing approaches describe neuron concepts by generating natural language descriptions, thereby advancing the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 ZeBin Ji , Yang Hu , Xiuli Bi , Bo Liu , Bin Xiao

Interpretability is an important property for visual models as it helps researchers and users understand the internal mechanism of a complex model. However, generating semantic explanations about the learned representation is challenging…

Computer Vision and Pattern Recognition · Computer Science 2022-04-12 Yu Yang , Seungbae Kim , Jungseock Joo

Advocates for Neuro-Symbolic Artificial Intelligence (NeSy) assert that combining deep learning with symbolic reasoning will lead to stronger AI than either paradigm on its own. As successful as deep learning has been, it is generally…

Artificial Intelligence · Computer Science 2022-12-16 Kyle Hamilton , Aparna Nayak , Bojan Božić , Luca Longo

ConceptLens is an innovative tool designed to illuminate the intricate workings of deep neural networks (DNNs) by visualizing hidden neuron activations. By integrating deep learning with symbolic methods, ConceptLens offers users a unique…

Machine Learning · Computer Science 2024-10-10 Abhilekha Dalal , Pascal Hitzler

Reasoning about images with rich text, such as charts and documents, is a critical application of vision-language models (VLMs). However, VLMs often struggle in these domains due to the scarcity of diverse text-rich vision-language data. To…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Yue Yang , Ajay Patel , Matt Deitke , Tanmay Gupta , Luca Weihs , Andrew Head , Mark Yatskar , Chris Callison-Burch , Ranjay Krishna , Aniruddha Kembhavi , Christopher Clark

Modern neural networks (NNs), trained on extensive raw sentence data, construct distributed representations by compressing individual words into dense, continuous, high-dimensional vectors. These representations are expected to capture…

Computation and Language · Computer Science 2024-12-04 Zhu Liu

Deep learning models have achieved strong performance in medical image analysis, but their internal decision processes remain difficult to interpret. Concept Bottleneck Models (CBMs) partially address this limitation by structuring…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Getamesay Dagnaw , Xuefei Yin , Muhammad Hassan Maqsood , Yanming Zhu , Alan Wee-Chung Liew

Representations in the hidden layers of Deep Neural Networks (DNN) are often hard to interpret since it is difficult to project them into an interpretable domain. Graph Convolutional Networks (GCN) allow this projection, but existing…

Computation and Language · Computer Science 2019-09-25 Robert Schwarzenberg , Marc Hübner , David Harbecke , Christoph Alt , Leonhard Hennig

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

Comprehending the rich semantics in an image and ordering them in linguistic order are essential to compose a visually-grounded and linguistically coherent description for image captioning. Modern techniques commonly capitalize on a…

Computer Vision and Pattern Recognition · Computer Science 2022-06-15 Yehao Li , Yingwei Pan , Ting Yao , Tao Mei

Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We propose an end-to-end…

Computation and Language · Computer Science 2017-12-25 Lajanugen Logeswaran , Honglak Lee , Dragomir Radev

Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reliability in high-stakes applications. They work by first extracting high-level concepts…

Machine Learning · Computer Science 2026-05-19 Samuele Bortolotti , Emanuele Marconato , Andrea Pugnana , Andrea Passerini , Stefano Teso