Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/36583
Title: | Modeling Implicit Bias with Fuzzy Cognitive Maps | Authors: | NAPOLES RUIZ, Gonzalo Grau, Isel CONCEPCION PEREZ, Leonardo KOUTSOVITI-KOUMERI, Lisa Papa, João Paulo |
Issue Date: | 2022 | Publisher: | ELSEVIER | Source: | Neurocomputing, | Abstract: | This paper presents a Fuzzy Cognitive Map model to quantify implicit bias in structured datasets where features can be numeric or discrete. In our proposal, problem features are mapped to neural concepts that are initially activated by experts when running what-if simulations, whereas weights connecting the neural concepts represent absolute correlation/association patterns between features. In addition, we introduce a new reasoning mechanism equipped with a normalization-like transfer function that prevents neurons from saturating. Another advantage of this new reasoning mechanism is that it can easily be controlled by regulating nonlinearity when updating neurons’ activation values in each iteration. Finally, we study the convergence of our model and derive analytical conditions concerning the existence and unicity of fixed-point attractors. | Keywords: | fairness;implicit bias;fuzzy cognitive maps;convergence analysis | Document URI: | http://hdl.handle.net/1942/36583 | ISSN: | 0925-2312 | e-ISSN: | 1872-8286 | DOI: | 10.1016/j.neucom.2022.01.070 | ISI #: | 000761785300004 | Rights: | 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). | Category: | A1 | Type: | Journal Contribution | Validations: | ecoom 2023 |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
1-s2.0-S092523122200090X-main.pdf | Published version | 1.25 MB | Adobe PDF | View/Open |
WEB OF SCIENCETM
Citations
18
checked on May 14, 2025
Page view(s)
40
checked on Sep 7, 2022
Download(s)
16
checked on Sep 7, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.