English
Related papers

Related papers: Geometrically Guided Integrated Gradients

200 papers

The explainability of machine learning algorithms is crucial, and numerous methods have emerged recently. Local, post-hoc methods assign an attribution score to each feature, indicating its importance for the prediction. However, these…

Machine Learning · Computer Science 2024-08-12 Giorgio Visani , Vincenzo Stanzione , Damien Garreau

State of the art machine learning algorithms are highly optimized to provide the optimal prediction possible, naturally resulting in complex models. While these models often outperform simpler more interpretable models by order of…

Machine Learning · Statistics 2016-11-24 Yotam Hechtlinger

It is widely recognized that the predictions of deep neural networks are difficult to parse relative to simpler approaches. However, the development of methods to investigate the mode of operation of such models has advanced rapidly in the…

Machine Learning · Computer Science 2020-07-08 Cosmas Heiß , Ron Levie , Cinjon Resnick , Gitta Kutyniok , Joan Bruna

The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in safety-critical applications. Most existing methods either…

Machine Learning · Computer Science 2021-02-25 Leo Schwinn , An Nguyen , René Raab , Leon Bungert , Daniel Tenbrinck , Dario Zanca , Martin Burger , Bjoern Eskofier

We introduce a neural implicit framework that exploits the differentiable properties of neural networks and the discrete geometry of point-sampled surfaces to approximate them as the level sets of neural implicit functions. To train a…

Graphics · Computer Science 2024-03-07 Tiago Novello , Guilherme Schardong , Luiz Schirmer , Vinicius da Silva , Helio Lopes , Luiz Velho

When solving inverse problems in geophysical imaging, deep generative models (DGMs) may be used to enforce the solution to display highly structured spatial patterns which are supported by independent information (e.g. the geological…

Geophysics · Physics 2021-04-28 Jorge Lopez-Alvis , Eric Laloy , Frédéric Nguyen , Thomas Hermans

Integrated Gradients (IG) and PatternAttribution (PA) are two established explainability methods for neural networks. Both methods are theoretically well-founded. However, they were designed to overcome different challenges. In this work,…

Machine Learning · Computer Science 2020-09-02 Robert Schwarzenberg , Steffen Castle

Machine learning classifiers are probabilistic in nature, and thus inevitably involve uncertainty. Predicting the probability of a specific input to be correct is called uncertainty (or confidence) estimation and is crucial for risk…

Machine Learning · Computer Science 2023-01-11 Gabriella Chouraqui , Liron Cohen , Gil Einziger , Liel Leman

Interpretability techniques aim to provide the rationale behind a model's decision, typically by explaining either an individual prediction (local explanation, e.g. 'why is this patient diagnosed with this condition') or a class of…

Implicit models, which allow for the generation of samples but not for point-wise evaluation of probabilities, are omnipresent in real-world problems tackled by machine learning and a hot topic of current research. Some examples include…

Machine Learning · Statistics 2018-04-27 Yingzhen Li , Richard E. Turner

Deep learning models have gained great popularity in statistical modeling because they lead to very competitive regression models, often outperforming classical statistical models such as generalized linear models. The disadvantage of deep…

Machine Learning · Computer Science 2021-07-26 Ronald Richman , Mario V. Wüthrich

One of the significant challenges of deep neural networks is that the complex nature of the network prevents human comprehension of the outcome of the network. Consequently, the applicability of complex machine learning models is limited in…

Computer Vision and Pattern Recognition · Computer Science 2020-06-22 Shailja Thakur , Sebastian Fischmeister

Deep learning has become the standard approach for most machine learning tasks. While its impact is undeniable, interpreting the predictions of deep learning models from a human perspective remains a challenge. In contrast to model…

Machine Learning · Computer Science 2023-11-13 Kyriakos Axiotis , Sami Abu-al-haija , Lin Chen , Matthew Fahrbach , Gang Fu

Calibration of large-scale differential equation models to observational or experimental data is a widespread challenge throughout applied sciences and engineering. A crucial bottleneck in state-of-the art calibration methods is the…

Optimization and Control · Mathematics 2021-02-23 Jon Cockayne , Andrew B. Duncan

Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. However, there has been little work on interpreting them, and specifically on understanding which parts of the graphs…

Computation and Language · Computer Science 2022-10-04 Michael Sejr Schlichtkrull , Nicola De Cao , Ivan Titov

Although neural networks have seen tremendous success as predictive models in a variety of domains, they can be overly confident in their predictions on out-of-distribution (OOD) data. To be viable for safety-critical applications, like…

Robotics · Computer Science 2022-11-17 Masha Itkina , Mykel J. Kochenderfer

The integration of contextual embeddings into the optimization processes of large language models is an advancement in natural language processing. The Context-Aware Neural Gradient Mapping framework introduces a dynamic gradient adjustment…

Computation and Language · Computer Science 2025-04-25 David Boldo , Lily Pemberton , Gabriel Thistledown , Jacob Fairchild , Felix Kowalski

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

Neural networks are trained primarily based on their inputs and outputs, without regard for their internal mechanisms. These neglected mechanisms determine properties that are critical for safety, like (i) transparency; (ii) the absence of…

Machine Learning · Computer Science 2024-12-02 Alex Cloud , Jacob Goldman-Wetzler , Evžen Wybitul , Joseph Miller , Alexander Matt Turner

The emergence of explainability methods has enabled a better comprehension of how deep neural networks operate through concepts that are easily understood and implemented by the end user. While most explainability methods have been designed…

Neurons and Cognition · Quantitative Biology 2022-03-17 Fernanda L. Ribeiro , Steffen Bollmann , Ross Cunnington , Alexander M. Puckett