通过通道响应感知训练的7GHz带宽光学25GMAC/sec/轴突光子神经网络

2021 European Conference on Optical Communication (ECOC) Pub Date : 2021-09-13 DOI:10.1109/ECOC52684.2021.9606097

G. Mourgias-Alexandris, A. Tsakyridis, N. Passalis, M. Kirtas, A. Tefas, T. Rutirawut, F. Gardes, N. Pleros, M. Moralis‐Pegios

{"title":"通过通道响应感知训练的7GHz带宽光学25GMAC/sec/轴突光子神经网络","authors":"G. Mourgias-Alexandris, A. Tsakyridis, N. Passalis, M. Kirtas, A. Tefas, T. Rutirawut, F. Gardes, N. Pleros, M. Moralis‐Pegios","doi":"10.1109/ECOC52684.2021.9606097","DOIUrl":null,"url":null,"abstract":"We present a channel response-aware Photonic Neural Network (PNN) and demonstrate experimentally its resilience in Inter-Symbol Interference (ISI) when implemented in an integrated neuron. The trained PNN model performs at 25GMAC/sec/axon using only 7GHz-bandwidth photonic axons with 97.37% accuracy in the MNIST dataset.","PeriodicalId":117375,"journal":{"name":"2021 European Conference on Optical Communication (ECOC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"title\":\"25GMAC/sec/axon photonic neural networks with 7GHz bandwidth optics through channel response-aware training\",\"authors\":\"G. Mourgias-Alexandris, A. Tsakyridis, N. Passalis, M. Kirtas, A. Tefas, T. Rutirawut, F. Gardes, N. Pleros, M. Moralis‐Pegios\",\"doi\":\"10.1109/ECOC52684.2021.9606097\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present a channel response-aware Photonic Neural Network (PNN) and demonstrate experimentally its resilience in Inter-Symbol Interference (ISI) when implemented in an integrated neuron. The trained PNN model performs at 25GMAC/sec/axon using only 7GHz-bandwidth photonic axons with 97.37% accuracy in the MNIST dataset.\",\"PeriodicalId\":117375,\"journal\":{\"name\":\"2021 European Conference on Optical Communication (ECOC)\",\"volume\":\"29 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 European Conference on Optical Communication (ECOC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ECOC52684.2021.9606097\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 European Conference on Optical Communication (ECOC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ECOC52684.2021.9606097","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 9

摘要

我们提出了一种通道响应感知光子神经网络(PNN)，并通过实验证明了它在集成神经元中实现时对符号间干扰(ISI)的弹性。训练后的PNN模型在MNIST数据集中仅使用7ghz带宽的光子轴突，以25GMAC/秒/轴突的速度运行，准确率为97.37%。

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

25GMAC/sec/axon photonic neural networks with 7GHz bandwidth optics through channel response-aware training

We present a channel response-aware Photonic Neural Network (PNN) and demonstrate experimentally its resilience in Inter-Symbol Interference (ISI) when implemented in an integrated neuron. The trained PNN model performs at 25GMAC/sec/axon using only 7GHz-bandwidth photonic axons with 97.37% accuracy in the MNIST dataset.

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

2021 European Conference on Optical Communication (ECOC)

自引率

0.00%

发文量