English
Related papers

Related papers: An Interpretable Neuron Embedding for Static Knowl…

200 papers

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

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

Machine Learning · Computer Science 2019-10-08 Yulong Wang , Xiaolin Hu , Hang Su

Deep neural networks (DNNs) with high expressiveness have achieved state-of-the-art performance in many tasks. However, their distributed feature representations are difficult to interpret semantically. In this work, human-interpretable…

Computer Vision and Pattern Recognition · Computer Science 2019-10-22 Jindong Gu , Volker Tresp

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

We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model,…

Computer Vision and Pattern Recognition · Computer Science 2017-04-20 David Bau , Bolei Zhou , Aditya Khosla , Aude Oliva , Antonio Torralba

We propose a new kind of embedding for natural language text that deeply represents semantic meaning. Standard text embeddings use the outputs from hidden layers of a pretrained language model. In our method, we let a language model learn…

Computation and Language · Computer Science 2022-11-22 Oleg Vasilyev , John Bohannon

Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing models to learn from new data while retaining previously…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Lu Yu , Zhe Tao , Dipam Goswami , Hantao Yao , Bartłomiej Twardowski , Joost Van de Weijer , Changsheng Xu

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

Integrating symbolic knowledge and data-driven learning algorithms is a longstanding challenge in Artificial Intelligence. Despite the recognized importance of this task, a notable gap exists due to the discreteness of symbolic…

Artificial Intelligence · Computer Science 2024-05-24 Gaia Saveri , Laura Nenzi , Luca Bortolussi , Jan Křetínský

Deep Neural Networks (DNNs) have advanced applications in domains such as healthcare, autonomous systems, and scene understanding, yet the internal semantics of their hidden neurons remain poorly understood. Prior work introduced a Concept…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Moumita Sen Sarma , Samatha Ereshi Akkamahadevi , Pascal Hitzler

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

In this work, we aim to leverage prior symbolic knowledge to improve the performance of deep models. We propose a graph embedding network that projects propositional formulae (and assignments) onto a manifold via an augmented Graph…

Artificial Intelligence · Computer Science 2019-10-30 Yaqi Xie , Ziwei Xu , Mohan S. Kankanhalli , Kuldeep S. Meel , Harold Soh

Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivity}$, i.e., they represent multiple unrelated features. A…

Machine Learning · Statistics 2023-10-19 David Klindt , Sophia Sanborn , Francisco Acosta , Frédéric Poitevin , Nina Miolane

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Computer Vision and Pattern Recognition · Computer Science 2021-01-22 Umberto Michieli , Pietro Zanuttigh

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures…

Artificial Intelligence · Computer Science 2018-06-11 Jingyi Xu , Zilu Zhang , Tal Friedman , Yitao Liang , Guy Van den Broeck

Deep Neural Networks have achieved huge success at a wide spectrum of applications from language modeling, computer vision to speech recognition. However, nowadays, good performance alone is not sufficient to satisfy the needs of practical…

Machine Learning · Computer Science 2018-12-31 Xuan Liu , Xiaoguang Wang , Stan Matwin

Knowledge distillation (KD) is one of the most useful techniques for light-weight neural networks. Although neural networks have a clear purpose of embedding datasets into the low-dimensional space, the existing knowledge was quite far from…

Computer Vision and Pattern Recognition · Computer Science 2021-04-29 Seunghyun Lee , Byung Cheol Song

With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern. Many approaches have been developed to tackle the problem through post-hoc analysis, such as explaining how predictions are made or…

Computer Vision and Pattern Recognition · Computer Science 2023-07-11 Haixing Dai , Lu Zhang , Lin Zhao , Zihao Wu , Zhengliang Liu , David Liu , Xiaowei Yu , Yanjun Lyu , Changying Li , Ninghao Liu , Tianming Liu , Dajiang Zhu
‹ Prev 1 2 3 10 Next ›