Next Article in Journal
Rootstock Effect on Volatile Composition of Albariño Wines
Previous Article in Journal
Electrochemical Corrosion of Galvanized Steel in Binary Sustainable Concrete Made with Sugar Cane Bagasse Ash (SCBA) and Silica Fume (SF) Exposed to Sulfates
Previous Article in Special Issue
Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps
Open AccessFeature PaperArticle

Emulating Cued Recall of Abstract Concepts via Regulated Activation Networks

Center of Informatics and Systems (CISUC), DEI, Polo-II University of Coimbra, Pinhal de Marrocos, 3030-290 Coimbra, Portugal
*
Author to whom correspondence should be addressed.
Current address: Centre for Informatics and Systems of the University of Coimbra Polo II, Pinhal de Marrocos, 3030-290 Coimbra, Portugal.
Dr. Rahul Sharma is the main contributor under the supervision of Dr. Bernardete Ribeiro, Dr. Alexandre Miguel Pinto, and Dr. Amílcar F. Cardoso.
Academic Editor: Attila Kovari
Appl. Sci. 2021, 11(5), 2134; https://doi.org/10.3390/app11052134
Received: 30 January 2021 / Revised: 21 February 2021 / Accepted: 22 February 2021 / Published: 28 February 2021
(This article belongs to the Special Issue Applied Cognitive Sciences)
Abstract concepts play a vital role in decision-making or recall operations because the associations among them are essential for contextual processing. Abstract concepts are complex and difficult to represent (conceptually, formally, or computationally), leading to difficulties in their comprehension and recall. This contribution reports the computational simulation of the cued recall of abstract concepts by exploiting their learned associations. The cued recall operation is realized via a novel geometric back-propagation algorithm that emulates the recall of abstract concepts learned through regulated activation network (RAN) modeling. During recall operation, another algorithm uniquely regulates the activation of concepts (nodes) by injecting excitatory, neutral, and inhibitory signals to other concepts of the same level. A Toy-data problem is considered to illustrate the RAN modeling and recall procedure. The results display how regulation enables contextual awareness among abstract nodes during the recall process. The MNIST dataset is used to show how recall operations retrieve intuitive and non-intuitive blends of abstract nodes. We show that every recall process converges to an optimal image. With more cues, better images are recalled, and every intermediate image obtained during the recall iterations corresponds to the varying cognitive states of the recognition procedure. View Full-Text
Keywords: computational psychology; computational cognitive modeling; machine learning; concept blending; conceptual combinations; recall; computational creativity computational psychology; computational cognitive modeling; machine learning; concept blending; conceptual combinations; recall; computational creativity
Show Figures

Figure 1

MDPI and ACS Style

Sharma, R.; Ribeiro, B.; Pinto, A.M.; Cardoso, A. Emulating Cued Recall of Abstract Concepts via Regulated Activation Networks. Appl. Sci. 2021, 11, 2134. https://doi.org/10.3390/app11052134

AMA Style

Sharma R, Ribeiro B, Pinto AM, Cardoso A. Emulating Cued Recall of Abstract Concepts via Regulated Activation Networks. Applied Sciences. 2021; 11(5):2134. https://doi.org/10.3390/app11052134

Chicago/Turabian Style

Sharma, Rahul; Ribeiro, Bernardete; Pinto, Alexandre M.; Cardoso, Amílcar. 2021. "Emulating Cued Recall of Abstract Concepts via Regulated Activation Networks" Appl. Sci. 11, no. 5: 2134. https://doi.org/10.3390/app11052134

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop