English
Related papers

Related papers: Towards falsifiable interpretability research

200 papers

Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same prediction made by the same model. In these cases, how do we…

Computation and Language · Computer Science 2021-04-14 Shuoyang Ding , Philipp Koehn

An intriguing property of deep neural networks is their inherent vulnerability to adversarial inputs, which significantly hinders their application in security-critical domains. Most existing detection methods attempt to use carefully…

Machine Learning · Computer Science 2017-12-05 Chanh Nguyen , Georgi Georgiev , Yujie Ji , Ting Wang

Providing explanations for deep neural networks (DNNs) is essential for their use in domains wherein the interpretability of decisions is a critical prerequisite. Despite the plethora of work on interpreting DNNs, most existing solutions…

Machine Learning · Computer Science 2021-01-26 Xinyang Zhang , Ren Pang , Shouling Ji , Fenglong Ma , Ting Wang

Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Bangjie Yin , Luan Tran , Haoxiang Li , Xiaohui Shen , Xiaoming Liu

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

Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, i.e., miniscule malicious changes to inputs may induce unintuitive outputs. One key approach to verify and mitigate such robustness issues is to falsify…

Cryptography and Security · Computer Science 2025-10-07 Raik Dankworth , Gesina Schwalbe

Deep neural networks (DNNs) have made a revolution in numerous fields during the last decade. However, in tasks with high safety requirements, such as medical or autonomous driving applications, providing an assessment of the models…

Machine Learning · Computer Science 2020-11-20 Omer Achrack , Raizy Kellerman , Ouriel Barzilay

Deep neural networks (DNNs) are the workhorses of deep learning, which constitutes the state of the art in numerous application domains. However, DNN-based decision rules are notoriously prone to poor generalization, i.e., may prove…

Machine Learning · Computer Science 2023-05-11 Guy Amir , Osher Maayan , Tom Zelazny , Guy Katz , Michael Schapira

With the rapid growth of machine learning, deep neural networks (DNNs) are now being used in numerous domains. Unfortunately, DNNs are "black-boxes", and cannot be interpreted by humans, which is a substantial concern in safety-critical…

Machine Learning · Computer Science 2023-02-10 Shahaf Bassan , Guy Katz

Complex nonlinear models such as deep neural network (DNNs) have become an important tool for image classification, speech recognition, natural language processing, and many other fields of application. These models however lack…

Without any means of interpretation, neural networks that predict molecular properties and bioactivities are merely black boxes. We will unravel these black boxes and will demonstrate approaches to understand the learned representations…

Machine Learning · Computer Science 2019-03-19 Kristina Preuer , Günter Klambauer , Friedrich Rippmann , Sepp Hochreiter , Thomas Unterthiner

Most recent work on interpretability of complex machine learning models has focused on estimating $\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\textit{Self-explaining}$ models where…

Machine Learning · Computer Science 2018-12-05 David Alvarez-Melis , Tommi S. Jaakkola

A common approach to quantifying neural text classifier interpretability is to calculate faithfulness metrics based on iteratively masking salient input tokens and measuring changes in the model prediction. We propose that this property is…

Computation and Language · Computer Science 2024-06-04 Evan Crothers , Herna Viktor , Nathalie Japkowicz

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

Generative AI models offer powerful capabilities but often lack transparency, making it difficult to interpret their output. This is critical in cases involving artistic or copyrighted content. This work introduces a search-inspired…

Artificial Intelligence · Computer Science 2025-04-03 Theodoros Aivalis , Iraklis A. Klampanos , Antonis Troumpoukis , Joemon M. Jose

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

Deep neural networks provide flexible frameworks for learning data representations and functions relating data to other properties and are often claimed to achieve 'super-human' performance in inferring relationships between input data and…

Materials Science · Physics 2021-05-26 Keith T. Butler , Manh Duc Le , Jeyarajan Thiyagalingam , Toby G. Perring

Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging. This paper presents an in-depth…

Machine Learning · Computer Science 2020-09-30 Dominique Mercier , Shoaib Ahmed Siddiqui , Andreas Dengel , Sheraz Ahmed

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
‹ Prev 1 4 5 6 7 8 10 Next ›