Oliver Espinosa-Meneses, M. Mejía-Lavalle, J. Ruiz, Gerardo Reyes, Miguel Pérez-Ramírez
{"title":"Spiking Neural Net to Solve the Shortest Path NP Problem","authors":"Oliver Espinosa-Meneses, M. Mejía-Lavalle, J. Ruiz, Gerardo Reyes, Miguel Pérez-Ramírez","doi":"10.1109/ICMEAE.2019.00020","DOIUrl":null,"url":null,"abstract":"Third Generation Artificial Neuronal Networks or Pulsed are suitable for solving problems in the field of Path Optimization, specifically in the shortest path problem. However, there are models of Pulse-Coupled Neural Network that need a large number of iterations before to find the shortest path between two points. This paper presents a variation of Pulse-Coupled Neural Network to solve the shortest path problem in an efficient way. This variant has a dynamic auto-wave propagation speed, which adjusts in a heuristic way to avoid iterations where there are no changes in the graph. To show the efficiency of the model, experiments are performed, and the results are compared against two other models of Pulsating Neural Networks. In the comparison, paradigms that use a static auto-wave speed and models with a dynamic auto-wave speed are used.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMEAE.2019.00020","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Third Generation Artificial Neuronal Networks or Pulsed are suitable for solving problems in the field of Path Optimization, specifically in the shortest path problem. However, there are models of Pulse-Coupled Neural Network that need a large number of iterations before to find the shortest path between two points. This paper presents a variation of Pulse-Coupled Neural Network to solve the shortest path problem in an efficient way. This variant has a dynamic auto-wave propagation speed, which adjusts in a heuristic way to avoid iterations where there are no changes in the graph. To show the efficiency of the model, experiments are performed, and the results are compared against two other models of Pulsating Neural Networks. In the comparison, paradigms that use a static auto-wave speed and models with a dynamic auto-wave speed are used.