English
Related papers

Related papers: Counterexample Classification

200 papers

The analysis of broken glass is forensically important to reconstruct the events of a criminal act. In particular, the comparison between the glass fragments found on a suspect (recovered cases) and those collected on the crime scene…

Applications · Statistics 2019-05-08 Laura Anderlucci , Francesca Fortunato , Angela Montanari

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…

Computation and Language · Computer Science 2024-05-21 Tom Roth , Inigo Jauregi Unanue , Alsharif Abuadbba , Massimo Piccardi

Novelty detection is a process for distinguishing the observations that differ in some respect from the observations that the model is trained on. Novelty detection is one of the fundamental requirements of a good classification or…

Computer Vision and Pattern Recognition · Computer Science 2019-04-10 Mahdyar Ravanbakhsh

Many binary classification problems minimize misclassification above (or below) a threshold. We show that instances of ranking problems, accuracy at the top or hypothesis testing may be written in this form. We propose a general framework…

Machine Learning · Computer Science 2020-02-26 Lukáš Adam , Václav Mácha , Václav Šmídl , Tomáš Pevný

Counterfactual explanations are viewed as an effective way to explain machine learning predictions. This interest is reflected by a relatively young literature with already dozens of algorithms aiming to generate such explanations. These…

Machine Learning · Computer Science 2022-12-05 Raphael Mazzine , David Martens

Detecting latent structure within a dataset is a crucial step in performing analysis of a dataset. However, existing state-of-the-art techniques for subclass discovery are limited: either they are limited to detecting very small numbers of…

Machine Learning · Computer Science 2021-11-09 Patrick Kage , Pavlos Andreadis

Post-hoc explanation methods are gaining popularity for interpreting, understanding, and debugging neural networks. Most analyses using such methods explain decisions in response to inputs drawn from the test set. However, the test set may…

Machine Learning · Computer Science 2020-12-17 Serena Booth , Yilun Zhou , Ankit Shah , Julie Shah

Models of physical systems are used to explain and predict experimental results and observations. When students encounter discrepancies between the actual and expected behavior of a system, they revise their models to include the newly…

Physics Education · Physics 2022-07-06 Laura Ríos , Benjamin Pollard , Dimitri R. Dounas-Frazer , H. J. Lewandowski

Conceptual analysis -- proposing definitions and refining them through counterexamples -- is central to philosophical methodology. We study whether language models can perform this task through iterated analysis and repair chains: one model…

Computation and Language · Computer Science 2026-05-06 Daniel Drucker , Kyle Mahowald

In the field of Explainable Artificial Intelligence (XAI), counterfactual examples explain to a user the predictions of a trained decision model by indicating the modifications to be made to the instance so as to change its associated…

Artificial Intelligence · Computer Science 2023-05-11 Thibault Laugel , Adulam Jeyasothy , Marie-Jeanne Lesot , Christophe Marsala , Marcin Detyniecki

We combine several folklore observations to provide a working framework for iterating constructions which contradict the axiom of choice. We use this to define a model in which any kind of structural failure must fail with a proper class of…

Logic · Mathematics 2021-07-26 Asaf Karagila

We report on an experiment in case outcome classification on European Court of Human Rights cases where our model first learns to identify the convention articles allegedly violated by the state from case facts descriptions, and…

Computation and Language · Computer Science 2023-02-14 T. Y. S. S Santosh , Marcel Perez San Blas , Phillip Kemper , Matthias Grabmair

A novel correction algorithm is proposed for multi-class classification problems with corrupted training data. The algorithm is non-intrusive, in the sense that it post-processes a trained classification model by adding a correction…

Machine Learning · Computer Science 2020-02-13 Jun Hou , Tong Qin , Kailiang Wu , Dongbin Xiu

Counterfactuals are widely used to explain ML model predictions by providing alternative scenarios for obtaining the more desired predictions. They can be generated by a variety of methods that optimize different, sometimes conflicting,…

Machine Learning · Computer Science 2024-08-05 Ignacy Stępka , Mateusz Lango , Jerzy Stefanowski

Multi-class novelty detection is increasingly becoming an important area of research due to the continuous increase in the number of object categories. It tries to answer the pertinent question: given a test sample, should we even try to…

Computer Vision and Pattern Recognition · Computer Science 2020-01-03 Supritam Bhattacharjee , Devraj Mandal , Soma Biswas

Multiclass classifiers are often designed and evaluated only on a sample from the classes on which they will eventually be applied. Hence, their final accuracy remains unknown. In this work we study how a classifier's performance over the…

Machine Learning · Computer Science 2024-05-29 Yuli Slavutsky , Yuval Benjamini

Understanding and explaining the mistakes made by trained models is critical to many machine learning objectives, such as improving robustness, addressing concept drift, and mitigating biases. However, this is often an ad hoc process that…

Machine Learning · Computer Science 2022-06-16 Abubakar Abid , Mert Yuksekgonul , James Zou

This study is about inducing classifiers using data that is imbalanced, with a minority class being under-represented in relation to the majority classes. The first section of this research focuses on the main characteristics of data that…

Machine Learning · Computer Science 2022-10-25 Shivaditya Shivganesh , Nitin Narayanan N , Pranav Murali , Ajaykumar M

The goal of an Intrusion Detection is inadequate to detect errors and unusual activity on a network or on the hosts belonging to a local network by monitoring network activity. Algorithms for building detection models are broadly classified…

Networking and Internet Architecture · Computer Science 2010-10-28 M. Sadiq Ali Khan

Counterfactual explanations can be obtained by identifying the smallest change made to a feature vector to qualitatively influence a prediction; for example, from 'loan rejected' to 'awarded' or from 'high risk of cardiovascular disease' to…

Machine Learning · Computer Science 2020-05-05 Martin Pawelczyk , Johannes Haug , Klaus Broelemann , Gjergji Kasneci