Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Annals of Computer Science and Information Systems

2 2023

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

QMAK: Interacting with Machine Learning Models and Visualizing Classification Process

Wojna Arkadiusz, Jachim Katarzyna, Kosson Łukasz, Kowalski Łukasz, Mański Damian, Mański Michał, Mroczek Krzysztof, Niemkiewicz Krzysztof, Piszczatowski Robert, Próchniak Maciej, Romańczuk Tomasz, Skibiński Piotr, Staszczyk Marcin, Szostakiewicz Michał, Tur Leszek, Wójcik Damian, Zuchniak Maciej

Annals of Computer Science and Information Systems

2023

Vol. 35

315--318

In various classification problems beside high accuracy data analysts expect often understanding and certain insight into the process of classification. To help them understand why a trained model selects a particular decision, how confident it is in the assigned decision, and to enable interactive improvement of trained models we present QMAK. The tool visualizes not only classification models but also the processes classifying individual objects. Five classical machine learning models and their classification process are visualized with QMAK: neural network, decision tree, k nearest neighbors, classifier based on principal component analysis (PCA) and rough set based classifier. QMAK provides also exemplary functions enabling users to modify trained models interactively.

Explainability in RIONA Algorithm Combining Rule Induction and Instance-Based Learning

Góra Grzegorz, Skowron Andrzej, Wojna Arkadiusz

Annals of Computer Science and Information Systems

2023

Vol. 35

491--502

The article concerns the well-known RIONA algorithm. We focus on the explainability property of this algorithm. The theoretical results, formulated and proved in the paper, show the relationships of the RIONA classifiers to both instance- and rule-based classifiers. In particular, we show the equivalence (relative to the classification) of the RIONA algorithm with the rule-based algorithm generating all consistent and maximally general rules from the neighbourhood of the test case. Consequently, the RIONA classifier can be represented by a rule-based classifier, with rules easily interpretable by humans. These theoretical results provide the explainability of the classifiers generated by RIONA and could be used in situations when an explanation or justification of the derived decision is important. It should be noted that the RIONA algorithm requires analysing only a small number of objects and rules contrary to algorithms based on the generation of huge sets of rules.