Pattern classification with Evolving Long-term Cognitive Networks
Authors:
- Gonzalo Nápoles,
- Agnieszka Jastrzębska,
- Yamisleydi Salgueiro
Abstract
This paper presents an interpretable neural system—termed Evolving Long-term Cognitive Network—for pattern classification. The proposed model was inspired by Fuzzy Cognitive Maps, which are interpretable recurrent neural networks for modeling and simulation. The network architecture is comprised of two neural blocks: a recurrent input layer and an output layer. The input layer is a Long-term Cognitive Network that gets unfolded in the same way as other recurrent neural networks, thus producing a sort of abstract hidden layers. In our model, we can attach meaningful linguistic labels to each neuron since the input neurons correspond to features in a given classification problem and the output neurons correspond to class labels. Moreover, we propose a variant of the backpropagation learning algorithm to compute the required parameters. This algorithm includes two new regularization components that are aimed at obtaining more interpretable knowledge representations. The numerical simulations using 58 datasets show that our model achieves higher prediction rates when compared with traditional white boxes while remaining competitive with the black boxes. Finally, we elaborate on the interpretability of our neural system using a proof of concept.
- Record ID
- WUT40d04748735a4a26bc4bc395a5ea370f
- Author
- Journal series
- Information Sciences, ISSN 0020-0255, e-ISSN 1872-6291
- Issue year
- 2021
- Vol
- 548
- Pages
- 461-478
- Publication size in sheets
- 0.85
- Keywords in Polish
- sieci kognitywne, rekurencyjne sieci neuronowe, propagacja wsteczna, interpretowalność
- Keywords in English
- Long-term Cognitive Networks, Recurrent neural networks, Backpropagation, Interpretability
- ASJC Classification
- ; ; ; ; ;
- Abstract in Polish
- W pracy przedstawione zostało nowe podejście do klasyfikacji wzorców oparte o sieci kognitywne. Zaproponowany model łączy model map kognitywnych z modelem rekurencyjnej sieci neuronowej. Jego główna zaleta to możliwość użycia wag modelu do interpretacji wpływu atrybutów na decyzję, czyli przypisanie do klasy. W artykule przedstawione zostało studium empiryczne porównujące nowy model z klasycznymi modelami służącymi do klasyfikacji.
- DOI
- DOI:10.1016/j.ins.2020.08.058 Opening in a new tab
- URL
- https://www.sciencedirect.com/science/article/pii/S0020025520308240 Opening in a new tab
- Language
- (en) English
- Score (nominal)
- 200
- Score source
- journalList
- Score
- = 200.0, 11-06-2021, ArticleFromJournal
- Publication indicators
- = 0; = 0; : 2018 = 2.636; : 2019 (2 years)= 5.91 - 2019 (5 years)=5.563
Share
- Uniform Resource Identifier
- https://repo.pw.edu.pl/info/article/WUT40d04748735a4a26bc4bc395a5ea370f/
- URN
urn:pw-repo:WUT40d04748735a4a26bc4bc395a5ea370f
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or PerishOpening in a new tab system.