English
Related papers

Related papers: A technical note on bilinear layers for interpreta…

200 papers

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high…

Computer Vision and Pattern Recognition · Computer Science 2018-02-15 Quanshi Zhang , Ying Nian Wu , Song-Chun Zhu

During the last years, Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in image classification. Their architectures have largely drawn inspiration by models of the primate visual system. However, while recent…

Computer Vision and Pattern Recognition · Computer Science 2017-08-24 Georgios Zoumpourlis , Alexandros Doumanoglou , Nicholas Vretos , Petros Daras

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

Machine Learning · Computer Science 2022-02-24 Jayneel Parekh , Pavlo Mozharovskyi , Florence d'Alché-Buc

Multivariate functions emerge naturally in a wide variety of data-driven models. Popular choices are expressions in the form of basis expansions or neural networks. While highly effective, the resulting functions tend to be hard to…

Machine Learning · Statistics 2022-06-15 Jan Decuyper , Koen Tiels , Siep Weiland , Mark C. Runacres , Johan Schoukens

Most existing interpretable methods explain a black-box model in a post-hoc manner, which uses simpler models or data analysis techniques to interpret the predictions after the model is learned. However, they (a) may derive contradictory…

Machine Learning · Computer Science 2020-01-22 Mengzhuo Guo , Qingpeng Zhang , Xiuwu Liao , Daniel Dajun Zeng

Deep learning models have achieved remarkable success in different areas of machine learning over the past decade; however, the size and complexity of these models make them difficult to understand. In an effort to make them more…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Vikram V. Ramaswamy , Sunnie S. Y. Kim , Nicole Meister , Ruth Fong , Olga Russakovsky

With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as model interpretation. While…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Hamed Behzadi-Khormouji , José Oramas

The coincidence similarity index, based on a combination of the Jaccard and overlap similarity indices, has noticeable properties in comparing and classifying data, including enhanced selectivity and sensitivity, intrinsic normalization,…

Neural and Evolutionary Computing · Computer Science 2023-08-29 Alexandre Benatti , Luciano da Fontoura Costa

Understanding the internal representations and decision mechanisms of deep neural networks remains a critical open challenge. While existing interpretability methods often identify influential input regions, they may not elucidate how a…

Machine Learning · Computer Science 2025-06-12 Farzaneh Mahdisoltani , Saeed Mahdisoltani , Roger B. Grosse , David J. Fleet

Deep neural networks can empirically perform efficient hierarchical learning, in which the layers learn useful representations of the data. However, how they make use of the intermediate representations are not explained by recent theories…

Machine Learning · Computer Science 2021-03-08 Minshuo Chen , Yu Bai , Jason D. Lee , Tuo Zhao , Huan Wang , Caiming Xiong , Richard Socher

Despite significant progress in transformer interpretability, an understanding of the computational mechanisms of large language models (LLMs) remains a fundamental challenge. Many approaches interpret a network's hidden representations but…

Machine Learning · Computer Science 2025-10-14 James R. Golden

There has been growing excitement over the possibility of employing artificial neural networks (ANNs) to gain new theoretical insight into the physics of quantum many-body problems. ``Interpretability'' remains a concern: can we understand…

Disordered Systems and Neural Networks · Physics 2020-12-08 Yi Zhang , Paul Ginsparg , Eun-Ah Kim

We regard explanations as a blending of the input sample and the model's output and offer a few definitions that capture various desired properties of the function that generates these explanations. We study the links between these…

Machine Learning · Computer Science 2020-01-16 Lior Wolf , Tomer Galanti , Tamir Hazan

Sparse autoencoders are a standard tool for uncovering interpretable latent representations in neural networks. Yet, their interpretation depends on the inputs, making their isolated study incomplete. Polynomials offer a solution; they…

Machine Learning · Computer Science 2025-10-21 Thomas Dooms , Ward Gauderis

Despite their increasing popularity and success in a variety of supervised learning problems, deep neural networks are extremely hard to interpret and debug: Given and already trained Deep Neural Net, and a set of test inputs, how can we…

Machine Learning · Computer Science 2018-06-07 Uday Singh Saini , Evangelos E. Papalexakis

Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks. Since deep features eventually transition from general to specific along deep networks, a fundamental problem of multi-task…

Machine Learning · Computer Science 2017-11-07 Mingsheng Long , Zhangjie Cao , Jianmin Wang , Philip S. Yu

MLP-like models built entirely upon multi-layer perceptrons have recently been revisited, exhibiting the comparable performance with transformers. It is one of most promising architectures due to the excellent trade-off between network…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Kecheng Zheng , Yang Cao , Kai Zhu , Ruijing Zhao , Zheng-Jun Zha

Even though neural networks have been long deployed in applications involving tabular data, still existing neural architectures are not explainable by design. In this paper, we propose a new class of interpretable neural networks for…

Machine Learning · Computer Science 2024-10-31 Arlind Kadra , Sebastian Pineda Arango , Josif Grabocka

Interpretability has become a necessary feature for machine learning models deployed in critical scenarios, e.g. legal system, healthcare. In these situations, algorithmic decisions may have (potentially negative) long-lasting effects on…

Machine Learning · Computer Science 2021-12-21 An-phi Nguyen , Maria Rodriguez Martinez

Neural networks currently dominate the machine learning community and they do so for good reasons. Their accuracy on complex tasks such as image classification is unrivaled at the moment and with recent improvements they are reasonably easy…

Machine Learning · Computer Science 2019-01-21 Sascha Saralajew , Lars Holdijk , Maike Rees , Thomas Villmann