Alexander Makarenko, "Multiple-Valued and Branching Neural Networks," Engineering World, vol. 2, pp. 20-28, 2020, DOI:
Alexander Makarenko. Multiple-Valued and Branching Neural Networks.
Engineering World. 2020;2:20-28.
Engineering World
E-ISSN: 2692-5079 An Open Access, Peer Reviewed Journal of Selected Publications in Engineering and Applied Sciences
Volume 2, 2020
Multiple-Valued and Branching Neural Networks
Author:
Abstract: The generalizations of common single-valued artificial neural networks are proposed. The main proposition is to consider multiple-valued networks. Such neural networks can have multiple values of elements and multivalued connections between elements at given time moment. Modified Hopfield neural networks with strong anticipation property are considered as the examples. New aspects of learning processes considered for the case of multiple-valuedness. Branching networks are described. Presumable applications of multivalued neural networks are proposed. Also some new research problems are described.
Keywords:
neuronets, multiple-valued, strong anticipation, Hopfield modification, generalizations, branching networks, applications
Pages: 20-28 DOI: *As the DOI is a unique identifier, it is already available in the pdf version.
**The DOI link will be activated in the first midst of January 2026.
WSEAS Transactions on Engineering World, E-ISSN: 2692-5079, Volume 2, 2020, Art. #4
×
Citation Tools