{"title":"故障神经网络","authors":"Shiuan-Wen Chen, Brendan Duke, P. Aarabi","doi":"10.1109/CAI54212.2023.00129","DOIUrl":null,"url":null,"abstract":"This study aims to investigate the response of the nervous system to injury through experiments using a neural network model trained with the MNIST dataset [1]. Multiple experiments are performed to examine the relationship between neural network damage and accuracy. How the damaged network can restore its functionality or accuracy with the aid of another neural network is also investigated. By analyzing these results, a better understanding of the nervous system’s ability to respond to injury and adapt to changes in neural networks can be gained.","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Faulty Neural Networks\",\"authors\":\"Shiuan-Wen Chen, Brendan Duke, P. Aarabi\",\"doi\":\"10.1109/CAI54212.2023.00129\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study aims to investigate the response of the nervous system to injury through experiments using a neural network model trained with the MNIST dataset [1]. Multiple experiments are performed to examine the relationship between neural network damage and accuracy. How the damaged network can restore its functionality or accuracy with the aid of another neural network is also investigated. By analyzing these results, a better understanding of the nervous system’s ability to respond to injury and adapt to changes in neural networks can be gained.\",\"PeriodicalId\":129324,\"journal\":{\"name\":\"2023 IEEE Conference on Artificial Intelligence (CAI)\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE Conference on Artificial Intelligence (CAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CAI54212.2023.00129\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE Conference on Artificial Intelligence (CAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CAI54212.2023.00129","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
This study aims to investigate the response of the nervous system to injury through experiments using a neural network model trained with the MNIST dataset [1]. Multiple experiments are performed to examine the relationship between neural network damage and accuracy. How the damaged network can restore its functionality or accuracy with the aid of another neural network is also investigated. By analyzing these results, a better understanding of the nervous system’s ability to respond to injury and adapt to changes in neural networks can be gained.