Logic and learning in network cascades

Bibliographic Data

ID6161600
AuthorsGalen Wilkerson (0000-0002-7957-5821, University of Surrey, corresponding author), Sotiris Moschoyianni (0000-0002-0164-8322, University of Surrey)
Year2021
Volume9
IssueS1
PagesS157-S174
Publication date2021-04-14
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueNetwork Science (JOURNAL)
Journal identifiersISSN: 2050-1250 • E-ISSN: 2050-1242
PublisherCambridge University Press (PUBLISHER • US)
DOI10.1017/nws.2021.3
OpenAlexW3153080980
LanguageEN
Citations received2
References cited42

Critical cascades are found in many self-organizing systems. Here, we examine critical cascades as a design paradigm for logic and learning under the linear threshold model (LTM), and simple biologically inspired variants of it as sources of computational power, learning efficiency, and robustness. First, we show that the LTM can compute logic, and with a small modification, universal Boolean logic, examining its stability and cascade frequency. We then frame it formally as a binary classifier and remark on implications for accuracy. Second, we examine the LTM as a statistical learning model, studying benefits of spatial constraints and criticality to efficiency. We also discuss implications for robustness in information encoding. Our experiments show that spatial constraints can greatly increase efficiency. Theoretical investigation and initial experimental results also indicate that criticality can result in a sudden increase in accuracy

Binary number · Cascade · Classifier (UML · Criticality · Machine learning · Robustness (evolution · Advanced Memory and Neural Computing · Computer Science · Mathematics · Neural dynamics and brain function · Neural Networks and Applications · Artificial Intelligence · Theoretical Computer Science

Tools

Open DOIOpen Access