{"title":"基于蚂蚁的连续神经拓扑搜索","authors":"AbdElRahman ElSaid","doi":"10.1016/j.simpa.2024.100615","DOIUrl":null,"url":null,"abstract":"<div><p>Ant-based Topology Search (ANTS) is a Neural Architecture Search (NAS) inspired by ant colony optimization (ACO). ANTS encodes the neural structure search space within a highly interconnected structure. Optimization agents, like ants, navigate this structure in search of an optimal neural topology. Continuous Ant-based Topology Search (CANTS) builds upon ANTS by replacing the discrete search space with a 3D continuous one. CANTS introduces a fourth dimension for potential neural synaptic weights, transitioning from NAS to NeuroEvolution (NE). This automates artificial neural network design without relying on backpropagation, reducing optimization time and offering a promising approach for machine learning applications.</p></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2024-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2665963824000034/pdfft?md5=097fa8999d88be8731a7066fd42c7a07&pid=1-s2.0-S2665963824000034-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Continuous Ant-Based Neural Topology Search\",\"authors\":\"AbdElRahman ElSaid\",\"doi\":\"10.1016/j.simpa.2024.100615\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Ant-based Topology Search (ANTS) is a Neural Architecture Search (NAS) inspired by ant colony optimization (ACO). ANTS encodes the neural structure search space within a highly interconnected structure. Optimization agents, like ants, navigate this structure in search of an optimal neural topology. Continuous Ant-based Topology Search (CANTS) builds upon ANTS by replacing the discrete search space with a 3D continuous one. CANTS introduces a fourth dimension for potential neural synaptic weights, transitioning from NAS to NeuroEvolution (NE). This automates artificial neural network design without relying on backpropagation, reducing optimization time and offering a promising approach for machine learning applications.</p></div>\",\"PeriodicalId\":29771,\"journal\":{\"name\":\"Software Impacts\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2024-01-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2665963824000034/pdfft?md5=097fa8999d88be8731a7066fd42c7a07&pid=1-s2.0-S2665963824000034-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Software Impacts\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2665963824000034\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Software Impacts","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2665963824000034","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0
摘要
蚁基拓扑搜索(ANTS)是一种神经结构搜索(NAS),其灵感来自蚁群优化(ACO)。ANTS 将神经结构搜索空间编码为一个高度互联的结构。优化代理就像蚂蚁一样,在这个结构中寻找最优的神经拓扑结构。基于蚂蚁的连续拓扑搜索(Continuous Ant-based Topology Search,CANTS)以 ANTS 为基础,用三维连续空间取代了离散搜索空间。CANTS 为潜在的神经突触权重引入了第四个维度,从 NAS 过渡到神经进化(NE)。这使人工神经网络设计自动化,无需依赖反向传播,减少了优化时间,为机器学习应用提供了一种前景广阔的方法。
Ant-based Topology Search (ANTS) is a Neural Architecture Search (NAS) inspired by ant colony optimization (ACO). ANTS encodes the neural structure search space within a highly interconnected structure. Optimization agents, like ants, navigate this structure in search of an optimal neural topology. Continuous Ant-based Topology Search (CANTS) builds upon ANTS by replacing the discrete search space with a 3D continuous one. CANTS introduces a fourth dimension for potential neural synaptic weights, transitioning from NAS to NeuroEvolution (NE). This automates artificial neural network design without relying on backpropagation, reducing optimization time and offering a promising approach for machine learning applications.