{"title":"仿生细胞:脑信息学的新前沿","authors":"Ziad Doughan, W. Itani, A. Haidar","doi":"10.1109/IMCET.2018.8603044","DOIUrl":null,"url":null,"abstract":"This paper introduces a new imitation of neurons cells, based on the latest discoveries in neuroscience. After reobserving the latest revelations in the field of biological neurons, the conventional artificial models has proven strong potentials in image processing and pattern classification, but remains far from presenting a modern imitation of natural intelligent organisms. A Biomimetic cell design is thus proposed with a combination of registers to hold the inputs, outputs, and weights as information codes. These cells use binary equivalence gates to compare the inputs to the weights and deliver the required outputs. The abstraction model provided renders the training process highly simplistic, which speeds up the design phase and opens the way towards a new dimension in artificial intelligence.","PeriodicalId":220641,"journal":{"name":"2018 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Biomimetic Cells: A New Frontier in Brain Informatics\",\"authors\":\"Ziad Doughan, W. Itani, A. Haidar\",\"doi\":\"10.1109/IMCET.2018.8603044\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper introduces a new imitation of neurons cells, based on the latest discoveries in neuroscience. After reobserving the latest revelations in the field of biological neurons, the conventional artificial models has proven strong potentials in image processing and pattern classification, but remains far from presenting a modern imitation of natural intelligent organisms. A Biomimetic cell design is thus proposed with a combination of registers to hold the inputs, outputs, and weights as information codes. These cells use binary equivalence gates to compare the inputs to the weights and deliver the required outputs. The abstraction model provided renders the training process highly simplistic, which speeds up the design phase and opens the way towards a new dimension in artificial intelligence.\",\"PeriodicalId\":220641,\"journal\":{\"name\":\"2018 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET)\",\"volume\":\"8 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IMCET.2018.8603044\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IMCET.2018.8603044","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Biomimetic Cells: A New Frontier in Brain Informatics
This paper introduces a new imitation of neurons cells, based on the latest discoveries in neuroscience. After reobserving the latest revelations in the field of biological neurons, the conventional artificial models has proven strong potentials in image processing and pattern classification, but remains far from presenting a modern imitation of natural intelligent organisms. A Biomimetic cell design is thus proposed with a combination of registers to hold the inputs, outputs, and weights as information codes. These cells use binary equivalence gates to compare the inputs to the weights and deliver the required outputs. The abstraction model provided renders the training process highly simplistic, which speeds up the design phase and opens the way towards a new dimension in artificial intelligence.