English
Related papers

Related papers: Compositional Explanations of Neurons

200 papers

Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks…

Artificial Intelligence · Computer Science 2018-02-05 Michael Harradon , Jeff Druce , Brian Ruttenberg

This paper is a write-up for the tutorial on "Fine-grained Interpretation and Causation Analysis in Deep NLP Models" that we are presenting at NAACL 2021. We present and discuss the research work on interpreting fine-grained components of a…

Computation and Language · Computer Science 2021-06-01 Hassan Sajjad , Narine Kokhlikyan , Fahim Dalvi , Nadir Durrani

Neural network models often generalize poorly to mismatched domains or distributions. In NLP, this issue arises in particular when models are expected to generalize compositionally, that is, to novel combinations of familiar words and…

Computation and Language · Computer Science 2021-11-10 Wang Zhu , Peter Shaw , Tal Linzen , Fei Sha

In this introductory article we present the basics of an approach to implementing computational interpreting of natural language aiming to model the meanings of words and phrases. Unlike other approaches, we attempt to define the meanings…

Computation and Language · Computer Science 2019-08-12 Michael Kapustin , Pavlo Kapustin

The pursuit of interpretable artificial intelligence has led to significant advancements in the development of methods that aim to explain the decision-making processes of complex models, such as deep learning systems. Among these methods,…

Machine Learning · Computer Science 2024-10-29 Yihao Zhang

Computational modeling plays an increasingly important role in neuroscience, highlighting the philosophical question of how computational models explain. In the context of neural network models for neuroscience, concerns have been raised…

Neurons and Cognition · Quantitative Biology 2021-04-15 Rosa Cao , Daniel Yamins

Deep neural networks drive the success of natural language processing. A fundamental property of language is its compositional structure, allowing humans to systematically produce forms for new meanings. For humans, languages with more…

Computation and Language · Computer Science 2025-01-10 Lukas Galke , Yoav Ram , Limor Raviv

Revealing the implicit semantic relation between the constituents of a noun-compound is important for many NLP applications. It has been addressed in the literature either as a classification task to a set of pre-defined relations or by…

Computation and Language · Computer Science 2018-05-08 Vered Shwartz , Ido Dagan

Artificial intelligence (AI) is currently based largely on black-box machine learning models which lack interpretability. The field of eXplainable AI (XAI) strives to address this major concern, being critical in high-stakes areas such as…

Artificial Intelligence · Computer Science 2024-06-26 Sean Tull , Robin Lorenz , Stephen Clark , Ilyas Khan , Bob Coecke

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

In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together. Although deep learning programs have demonstrated…

Machine Learning · Computer Science 2021-10-27 Mike Wu , Noah Goodman , Stefano Ermon

Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability. While recent developments in explainable artificial intelligence attempt…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Yunhao Ge , Yao Xiao , Zhi Xu , Meng Zheng , Srikrishna Karanam , Terrence Chen , Laurent Itti , Ziyan Wu

Neural module networks (NMNs) are a popular approach for modeling compositionality: they achieve high accuracy when applied to problems in language and vision, while reflecting the compositional structure of the problem in the network…

Computation and Language · Computer Science 2020-09-09 Sanjay Subramanian , Ben Bogin , Nitish Gupta , Tomer Wolfson , Sameer Singh , Jonathan Berant , Matt Gardner

Concept-based interpretability methods offer a lens into the internals of foundation models by decomposing their embeddings into high-level concepts. These concept representations are most useful when they are compositional, meaning that…

Computation and Language · Computer Science 2024-06-27 Adam Stein , Aaditya Naik , Yinjun Wu , Mayur Naik , Eric Wong

Compositionality is a hallmark of human language that not only enables linguistic generalization, but also potentially facilitates acquisition. When simulating language emergence with neural networks, compositionality has been shown to…

Computation and Language · Computer Science 2023-05-23 Emily Cheng , Mathieu Rita , Thierry Poibeau

One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Pavel Tokmakov , Yu-Xiong Wang , Martial Hebert

Rule-based explanation methods offer rigorous and globally interpretable insights into neural network behavior. However, existing approaches are mostly limited to small fully connected networks and depend on costly layerwise rule extraction…

Machine Learning · Computer Science 2025-10-16 Chuqin Geng , Anqi Xing , Li Zhang , Ziyu Zhao , Yuhe Jiang , Xujie Si

Deep neural networks are becoming more and more popular due to their revolutionary success in diverse areas, such as computer vision, natural language processing, and speech recognition. However, the decision-making processes of these…

Computation and Language · Computer Science 2021-10-15 Oana-Maria Camburu

The principle of compositionality, which enables natural language to represent complex concepts via a structured combination of simpler ones, allows us to convey an open-ended set of messages using a limited vocabulary. If compositionality…

Computation and Language · Computer Science 2020-02-18 Yi Ren , Shangmin Guo , Matthieu Labeau , Shay B. Cohen , Simon Kirby

Computer vision systems in real-world applications need to be robust to partial occlusion while also being explainable. In this work, we show that black-box deep convolutional neural networks (DCNNs) have only limited robustness to partial…

Computer Vision and Pattern Recognition · Computer Science 2020-06-30 Adam Kortylewski , Qing Liu , Angtian Wang , Yihong Sun , Alan Yuille