no code implementations • 25 Apr 2024 • Evandro S. Ortigossa, Fábio F. Dias, Brian Barr, Claudio T. Silva, Luis Gustavo Nonato
The development of machine learning applications has increased significantly in recent years, motivated by the remarkable ability of learning-powered systems to discover and generalize intricate patterns hidden in massive datasets.
1 code implementation • 19 Feb 2024 • Wei zhang, Brian Barr, John Paisley
Deep neural networks have revolutionized many fields, but their black-box nature also occasionally prevents their wider adoption in fields such as healthcare and finance, where interpretable and explainable models are required.
no code implementations • 13 Nov 2023 • Brian Barr, Noah Fatsi, Leif Hancox-Li, Peter Richter, Daniel Proano, Caleb Mok
The field of explainable artificial intelligence (XAI) aims to explain how black-box machine learning models work.
no code implementations • 27 Jul 2022 • Peter Xenopoulos, Joao Rulff, Luis Gustavo Nonato, Brian Barr, Claudio Silva
Calibrate constructs a reliability diagram that is resistant to drawbacks in traditional approaches, and allows for interactive subgroup analysis and instance-level inspection.
1 code implementation • 12 Jul 2022 • Isha Hameed, Samuel Sharpe, Daniel Barcklow, Justin Au-Yeung, Sahil Verma, Jocelyn Huang, Brian Barr, C. Bayan Bruss
By perturbing the input variables in rank order of importance, the goal is to assess the sensitivity of the model's performance.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
1 code implementation • 19 Jan 2022 • Jun Yuan, Brian Barr, Kyle Overton, Enrico Bertini
We also contribute SuRE, a visual analytics (VA) system that integrates HSR and interactive surrogate rule visualizations.
no code implementations • 6 Jan 2022 • Peter Xenopoulos, Gromit Chan, Harish Doraiswamy, Luis Gustavo Nonato, Brian Barr, Claudio Silva
Furthermore, due to the stochastic nature of some explainability methods, it is possible for different runs of a method to produce contradictory explanations for a given observation.
no code implementations • 2 Dec 2021 • Brian Barr, Matthew R. Harrington, Samuel Sharpe, C. Bayan Bruss
Counterfactual explanations represent the minimal change to a data sample that alters its predicted classification, typically from an unfavorable initial class to a desired target class.
no code implementations • 16 Dec 2020 • Rachana Balasubramanian, Samuel Sharpe, Brian Barr, Jason Wittenbach, C. Bayan Bruss
In the environment of fair lending laws and the General Data Protection Regulation (GDPR), the ability to explain a model's prediction is of paramount importance.
1 code implementation • 20 Jul 2020 • Brian Barr, Ke Xu, Claudio Silva, Enrico Bertini, Robert Reilly, C. Bayan Bruss, Jason D. Wittenbach
In data science, there is a long history of using synthetic data for method development, feature selection and feature engineering.