11 citations · 19 across the 12 of their papers we have counts for
13 papers
Why this and not that? A Logic-based Framework for Contrastive Explanations
Tobias Geibinger, Reijo Jaakkola, Antti Kuusisto +2
We define several canonical problems related to contrastive explanations, each answering a question of the form ''Why P but not Q?''. The problems compute causes for both P and Q,…
Globally Interpretable Classifiers via Boolean Formulas with Dynamic Propositions
Reijo Jaakkola, Tomi Janhunen, Antti Kuusisto +2
Interpretability and explainability are among the most important challenges of modern artificial intelligence, being mentioned even in various legislative sources. In this article,…
Description Complexity of Unary Structures in First-Order Logic with Links to Entropy
Reijo Jaakkola, Antti Kuusisto, Miikka Vilander
The description complexity of a model is the length of the shortest formula that defines the model. We study the description complexity of unary structures in first-order logic FO,…
Interpretable classifiers for tabular data via discretization and feature selection
Reijo Jaakkola, Tomi Janhunen, Antti Kuusisto +2
We introduce a method for computing immediately human interpretable yet accurate classifiers from tabular data. The classifiers obtained are short Boolean formulas, computed via fi…
Short Boolean Formulas as Explanations in Practice
Reijo Jaakkola, Tomi Janhunen, Antti Kuusisto +2
We investigate explainability via short Boolean formulas in the data model based on unary relations. As an explanation of length k, we take a Boolean formula of length k that minim…
A monotone connection between model class size and description length
Reijo Jaakkola, Antti Kuusisto, Miikka Vilander
This paper links sizes of model classes to the minimum lengths of their defining formulas, that is, to their description complexities. Limiting to models with a fixed domain of siz…