{"title":"门网控制对ResNets的解释","authors":"Changcun Huang","doi":"10.1162/neco_a_01600","DOIUrl":null,"url":null,"abstract":"This letter first constructs a typical solution of ResNets for multicategory classifications based on the idea of the gate control of LSTMs, from which a general interpretation of the ResNet architecture is given and the performance mechanism is explained. We also use more solutions to further demonstrate the generality of that interpretation. The classification result is then extended to the universal-approximation capability of the type of ResNet with two-layer gate networks, an architecture that was proposed in an original paper of ResNets and has both theoretical and practical significance.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"On an Interpretation of ResNets via Gate-Network Control\",\"authors\":\"Changcun Huang\",\"doi\":\"10.1162/neco_a_01600\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This letter first constructs a typical solution of ResNets for multicategory classifications based on the idea of the gate control of LSTMs, from which a general interpretation of the ResNet architecture is given and the performance mechanism is explained. We also use more solutions to further demonstrate the generality of that interpretation. The classification result is then extended to the universal-approximation capability of the type of ResNet with two-layer gate networks, an architecture that was proposed in an original paper of ResNets and has both theoretical and practical significance.\",\"PeriodicalId\":54731,\"journal\":{\"name\":\"Neural Computation\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2023-08-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neural Computation\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10302046/\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Computation","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10302046/","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
On an Interpretation of ResNets via Gate-Network Control
This letter first constructs a typical solution of ResNets for multicategory classifications based on the idea of the gate control of LSTMs, from which a general interpretation of the ResNet architecture is given and the performance mechanism is explained. We also use more solutions to further demonstrate the generality of that interpretation. The classification result is then extended to the universal-approximation capability of the type of ResNet with two-layer gate networks, an architecture that was proposed in an original paper of ResNets and has both theoretical and practical significance.
期刊介绍:
Neural Computation is uniquely positioned at the crossroads between neuroscience and TMCS and welcomes the submission of original papers from all areas of TMCS, including: Advanced experimental design; Analysis of chemical sensor data; Connectomic reconstructions; Analysis of multielectrode and optical recordings; Genetic data for cell identity; Analysis of behavioral data; Multiscale models; Analysis of molecular mechanisms; Neuroinformatics; Analysis of brain imaging data; Neuromorphic engineering; Principles of neural coding, computation, circuit dynamics, and plasticity; Theories of brain function.