English
Related papers

Related papers: A Logic of "Black Box" Classifier Systems

200 papers

We define a strongly normalising proof-net calculus corresponding to the logic of strongly compact closed categories with biproducts. The calculus is a full and faithful representation of the free strongly compact closed category with…

Quantum Physics · Physics 2013-06-20 Samson Abramsky , Ross Duncan

Algorithmic fairness literature presents numerous mathematical notions and metrics, and also points to a tradeoff between them while satisficing some or all of them simultaneously. Furthermore, the contextual nature of fairness notions…

Human-Computer Interaction · Computer Science 2022-02-17 Mukund Telukunta , Venkata Sriram Siddhardh Nadendla

Multilabel classification is a relatively recent subfield of machine learning. Unlike to the classical approach, where instances are labeled with only one category, in multilabel classification, an arbitrary number of categories is chosen…

Artificial Intelligence · Computer Science 2013-03-01 Alfonso E. Romero , Luis M. de Campos

Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…

Machine Learning · Computer Science 2022-06-03 Aparna Balagopalan , Haoran Zhang , Kimia Hamidieh , Thomas Hartvigsen , Frank Rudzicz , Marzyeh Ghassemi

Recent work has shown that some common machine learning classifiers can be compiled into Boolean circuits that have the same input-output behavior. We present a theory for unveiling the reasons behind the decisions made by Boolean…

Artificial Intelligence · Computer Science 2020-04-21 Adnan Darwiche , Auguste Hirth

Probabilistic numerics casts numerical tasks, such the numerical solution of differential equations, as inference problems to be solved. One approach is to model the unknown quantity of interest as a random variable, and to constrain this…

Numerical Analysis · Mathematics 2021-10-29 Onur Teymur , Christopher N. Foley , Philip G. Breen , Toni Karvonen , Chris. J. Oates

We introduce the notion of pointwise coverage to measure the explainability properties of machine learning classifiers. An explanation for a prediction is a definably simple region of the feature space sharing the same label as the…

Machine Learning · Computer Science 2019-10-24 Brett Mullins

The vast majority of real world classification problems are imbalanced, meaning there are far fewer data from the class of interest (the positive class) than from other classes. We propose two machine learning algorithms to handle highly…

Machine Learning · Statistics 2014-06-10 Siong Thye Goh , Cynthia Rudin

Two types of explanations have been receiving increased attention in the literature when analyzing the decisions made by classifiers. The first type explains why a decision was made and is known as a sufficient reason for the decision, also…

Artificial Intelligence · Computer Science 2023-07-25 Chunxi Ji , Adnan Darwiche

Explainability is motivated by the lack of transparency of black-box Machine Learning approaches, which do not foster trust and acceptance of Machine Learning algorithms. This also happens in the Predictive Process Monitoring field, where…

Artificial Intelligence · Computer Science 2025-07-25 Williams Rizzi , Marco Comuzzi , Chiara Di Francescomarino , Chiara Ghidini , Suhwan Lee , Fabrizio Maria Maggi , Alexander Nolte

In the practical deployment of machine learning (ML) models, missing data represents a recurring challenge. Missing data is often addressed when training ML models. But missing data also needs to be addressed when deciding predictions and…

Artificial Intelligence · Computer Science 2023-06-29 Ramón Béjar , António Morgado , Jordi Planes , Joao Marques-Silva

An inductive logic can be formulated in which the elements are not propositions or probability distributions, but information systems. The logic is complete for information systems with binary hypotheses, i.e., it applies to all such…

Artificial Intelligence · Computer Science 2013-04-11 Norman C. Dalkey

Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision…

Machine Learning · Computer Science 2021-01-21 Nadia Burkart , Marco F. Huber

Pattern recognition systems implemented using deep neural networks achieve better results than linear models. However, their drawback is the black box property. This property means that one with no experience utilising nonlinear systems may…

Machine Learning · Computer Science 2024-01-29 Martin Klimo , Lubomir Kralik

Explainability techniques for data-driven predictive models based on artificial intelligence and machine learning algorithms allow us to better understand the operation of such systems and help to hold them accountable. New transparency…

Machine Learning · Computer Science 2022-09-09 Kacper Sokol , Alexander Hepburn , Raul Santos-Rodriguez , Peter Flach

The widespread adoption of black-box models in Artificial Intelligence has enhanced the need for explanation methods to reveal how these obscure models reach specific decisions. Retrieving explanations is fundamental to unveil possible…

Artificial Intelligence · Computer Science 2021-02-26 Francesco Bodria , Fosca Giannotti , Riccardo Guidotti , Francesca Naretto , Dino Pedreschi , Salvatore Rinzivillo

Positive-unlabeled learning (PUL) aims at learning a binary classifier from only positive and unlabeled training data. Even though real-world applications often involve imbalanced datasets where the majority of examples belong to one class,…

Machine Learning · Statistics 2024-03-12 Emilio Dorigatti , Jann Goschenhofer , Benjamin Schubert , Mina Rezaei , Bernd Bischl

Multi-class classification methods that produce sets of probabilistic classifiers, such as ensemble learning methods, are able to model aleatoric and epistemic uncertainty. Aleatoric uncertainty is then typically quantified via the Bayes…

Machine Learning · Statistics 2023-04-20 Thomas Mortier , Viktor Bengs , Eyke Hüllermeier , Stijn Luca , Willem Waegeman

In this short note we relate some known properties of propositional calculus to purely algebraic considerations of a Boolean algebra. Classes of formulas of propositional calculus are considered as elements of a Boolean algebra. As such…

Logic · Mathematics 2009-06-12 Bernd R. Schuh

Multi-label classification (MLC) is a supervised learning problem in which, contrary to standard multiclass classification, an instance can be associated with several class labels simultaneously. In this chapter, we advocate a rule-based…

Machine Learning · Computer Science 2020-12-09 Eneldo Loza Mencía , Johannes Fürnkranz , Eyke Hüllermeier , Michael Rapp