English
Related papers

Related papers: Respect the model: Fine-grained and Robust Explana…

200 papers

Attribution methods can provide powerful insights into the reasons for a classifier's decision. We argue that a key desideratum of an explanation method is its robustness to input hyperparameters which are often randomly set or empirically…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Naman Bansal , Chirag Agarwal , Anh Nguyen

Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons, and standard RL methods provide too few tools to provide insight into the…

Machine Learning · Computer Science 2022-10-24 James MacGlashan , Evan Archer , Alisa Devlic , Takuma Seno , Craig Sherstan , Peter R. Wurman , Peter Stone

This paper presents a new method for reconstructing regions of interest (ROI) from a limited number of computed tomography (CT) measurements. Classical model-based iterative reconstruction methods lead to images with predictable features.…

Image and Video Processing · Electrical Eng. & Systems 2023-05-18 Marion Savanier , Emilie Chouzenoux , Jean-Christophe Pesquet , Cyril Riddell

We introduce a pruning algorithm that provably sparsifies the parameters of a trained model in a way that approximately preserves the model's predictive accuracy. Our algorithm uses a small batch of input points to construct a data-informed…

Machine Learning · Computer Science 2021-03-16 Cenk Baykal , Lucas Liebenwein , Igor Gilitschenski , Dan Feldman , Daniela Rus

A key task in actuarial modelling involves modelling the distributional properties of losses. Classic (distributional) regression approaches like Generalized Linear Models (GLMs; Nelder and Wedderburn, 1972) are commonly used, but…

Machine Learning · Statistics 2024-06-04 Benjamin Avanzi , Eric Dong , Patrick J. Laub , Bernard Wong

The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Subhabrata Choudhury , Iro Laina , Christian Rupprecht , Andrea Vedaldi

EXplainable AI (XAI) is an essential topic to improve human understanding of deep neural networks (DNNs) given their black-box internals. For computer vision tasks, mainstream pixel-based XAI methods explain DNN decisions by identifying…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Ao Sun , Pingchuan Ma , Yuanyuan Yuan , Shuai Wang

The new era of image segmentation leveraging the power of Deep Neural Nets (DNNs) comes with a price tag: to train a neural network for pixel-wise segmentation, a large amount of training samples has to be manually labeled on…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Clemens Seibold , Johannes Künzel , Anna Hilsmann , Peter Eisert

The information of spiking neural networks (SNNs) are propagated between the adjacent biological neuron by spikes, which provides a computing paradigm with the promise of simulating the human brain. Recent studies have found that the time…

Neural and Evolutionary Computing · Computer Science 2022-05-05 Pengfei Sun , Longwei Zhu , Dick Botteldooren

Machine Learning algorithms are increasingly being used in recent years due to their flexibility in model fitting and increased predictive performance. However, the complexity of the models makes them hard for the data analyst to interpret…

Machine Learning · Statistics 2018-06-07 Joel Vaughan , Agus Sudjianto , Erind Brahimi , Jie Chen , Vijayan N. Nair

Neural network models are widely used in a variety of domains, often as black-box solutions, since they are not directly interpretable for humans. The field of explainable artificial intelligence aims at developing explanation methods to…

Machine Learning · Computer Science 2023-07-25 Patrik Hammersborg , Inga Strümke

Distributions measured in high energy physics experiments are usually distorted and/or transformed by various detector effects. A regularization method for unfolding these distributions is re-formulated in terms of the Singular Value…

High Energy Physics - Phenomenology · Physics 2008-11-26 Andreas Hoecker , Vakhtang Kartvelishvili

Despite the recent, widespread focus on eXplainable AI (XAI), explanations computed by XAI methods tend to provide little insight into the functioning of Neural Networks (NNs). We propose a novel framework for obtaining (local) explanations…

Artificial Intelligence · Computer Science 2021-06-15 Emanuele Albini , Piyawat Lertvittayakumjorn , Antonio Rago , Francesca Toni

Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more concentrated on the objects associated with the image's…

Machine Learning · Computer Science 2021-10-07 Zifan Wang , Matt Fredrikson , Anupam Datta

Artificial Intelligence (AI) has become essential for analyzing complex data and solving highly-challenging tasks. It is being applied across numerous disciplines beyond computer science, including Food Engineering, where there is a growing…

In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings of these black box models remains challenging, yet crucial…

Machine Learning · Statistics 2024-04-18 Niklas Koenen , Marvin N. Wright

The reflection superposition phenomenon is complex and widely distributed in the real world, which derives various simplified linear and nonlinear formulations of the problem. In this paper, based on the investigation of the weaknesses of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Qiming Hu , Xiaojie Guo

Network slicing aims to enhance flexibility and efficiency in next-generation wireless networks by allocating the right resources to meet the diverse requirements of various applications. Managing these slices with machine learning (ML)…

Networking and Internet Architecture · Computer Science 2025-01-28 Shavbo Salehi , Pedro Enrique Iturria-Rivera , Medhat Elsayed , Majid Bavand , Raimundas Gaigalas , Yigit Ozcan , Melike Erol-Kantarci

Explainability and interpretability of AI models is an essential factor affecting the safety of AI. While various explainable AI (XAI) approaches aim at mitigating the lack of transparency in deep networks, the evidence of the effectiveness…

Artificial Intelligence · Computer Science 2020-03-03 Kamran Alipour , Jurgen P. Schulze , Yi Yao , Avi Ziskind , Giedrius Burachas

Incorporating uncertainty is crucial to provide trustworthy explanations of deep learning models. Recent works have demonstrated how uncertainty modeling can be particularly important in the unsupervised field of representation learning…

Machine Learning · Computer Science 2024-12-12 Kristoffer K. Wickstrøm , Thea Brüsch , Michael C. Kampffmeyer , Robert Jenssen