随机与BFGS训练在射频调制神经识别中的应用

Proceedings of The 6th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2022) Pub Date : 2022-11-14 DOI:10.22323/1.429.0011

M. Dima, M. Dima, M. Mihailescu

{"title":"随机与BFGS训练在射频调制神经识别中的应用","authors":"M. Dima, M. Dima, M. Mihailescu","doi":"10.22323/1.429.0011","DOIUrl":null,"url":null,"abstract":"Neuromorphic classification of RF-Modulation type is an on-going topic in SIGINT applications. Neural network training approaches are varied, each being suited to a certain application. For exemplification I show the results for BFGS (Broyden-Fletcher-Goldfarb-Shanno) optimization in discriminating AM vs FM modulation and of stochastic optimization for the challenging case of AM-LSB vs. AM-USB (upper / lower sideband) discrimination. Although slower than BFGS, the stochastic training of a neural network avoids better local minima, obtaining a stable neurocore.","PeriodicalId":262901,"journal":{"name":"Proceedings of The 6th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2022)","volume":"225 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Stochastic vs. BFGS Training in Neural Discrimination of RF-Modulation\",\"authors\":\"M. Dima, M. Dima, M. Mihailescu\",\"doi\":\"10.22323/1.429.0011\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Neuromorphic classification of RF-Modulation type is an on-going topic in SIGINT applications. Neural network training approaches are varied, each being suited to a certain application. For exemplification I show the results for BFGS (Broyden-Fletcher-Goldfarb-Shanno) optimization in discriminating AM vs FM modulation and of stochastic optimization for the challenging case of AM-LSB vs. AM-USB (upper / lower sideband) discrimination. Although slower than BFGS, the stochastic training of a neural network avoids better local minima, obtaining a stable neurocore.\",\"PeriodicalId\":262901,\"journal\":{\"name\":\"Proceedings of The 6th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2022)\",\"volume\":\"225 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of The 6th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2022)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.22323/1.429.0011\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of The 6th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2022)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.22323/1.429.0011","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

射频调制类型的神经形态分类是SIGINT应用中一个不断发展的课题。神经网络训练方法多种多样，每一种都适合于特定的应用。举例来说，我展示了BFGS (Broyden-Fletcher-Goldfarb-Shanno)优化在分辨AM和FM调制方面的结果，以及随机优化在分辨AM- lsb和AM- usb(上/下边带)方面的结果。虽然比BFGS慢，但神经网络的随机训练避免了更好的局部极小值，获得了稳定的神经核。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Stochastic vs. BFGS Training in Neural Discrimination of RF-Modulation

Neuromorphic classification of RF-Modulation type is an on-going topic in SIGINT applications. Neural network training approaches are varied, each being suited to a certain application. For exemplification I show the results for BFGS (Broyden-Fletcher-Goldfarb-Shanno) optimization in discriminating AM vs FM modulation and of stochastic optimization for the challenging case of AM-LSB vs. AM-USB (upper / lower sideband) discrimination. Although slower than BFGS, the stochastic training of a neural network avoids better local minima, obtaining a stable neurocore.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of The 6th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2022)

自引率

0.00%

发文量