Multiple-Valued and Branching Neural Networks
Journal: Engineering World (Vol.2, No. -)Publication Date: 2020-12-31
Authors : Alexander Makarenko;
Page : 20-28
Keywords : neuronets; multiple-valued; strong anticipation; Hopfield modification; generalizations; branching networks; applications;
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.
Other Latest Articles
- Fuzzy Cognitive Map Methodology For Evaluating Material Selection Criteria
- A Novel Approach for Patient Anatomized Authentication scheme using Smart Card in Telecare Medical Information System
- Consumption temporary density for the detection of water leakages in real-time
- Quantitation of human Telomerase Reverse Transcriptase (hTERT) level in normospermic man using ELISA method
Last modified: 2020-08-04 23:41:28