维普期刊资源整合服务平台（V6.5）

维普中文期刊产品整合服务

7篇 您的检索式：作者名="Anastasios Tefas"

选中清除导出查看参考文献查看引证文献引用追踪共1页首页上一页第1页下一页末页 /1 跳转

		题名	作者	年代	出处	被引量
	1	Salient feature and reliable classifier selection for facial expression classification显示文摘	Marios Kyperountas Anastasios Tefas Ioannis Pitas	2010	Pattern Recognition2010，43，3：	1
	2	using Support Vector Machines to Enhance the performance of Elastic graph Mathing for Frontal Face Authentication显示文摘	Anastasios Tefas	2001	trane on pattern AnalysisAnd Machine Intelligence2001，23，7：	1
	3	Multiplicative update rules for concurrent nonnegative matrix factorization and maximum margin classification显示文摘	ZOIDI Olga TEFAS Anastasios PITAS Ioannis	2013	IEEE Transactions on Neural Networks and Learning Systems2013，24，3：	1
	4	Weighted piecewise LDA for solving the small sample size problem in face verification 显示文摘	Marios Kyperountas Anastasios Tefas Ioannis Pitas	2007	IEEE Transactions on Neural Networks2007，18，2：	1
	5	Optimizing linear discdminant error correcting output codes using particle swarm optimization显示文摘	Dimilrios Bouzas Nikolaos Arvanitopoulos Anastasios Tefas	2011	Lecture Notes in Com- puter Science2011，6792，4：	1
	6	DropELM:Fast neural network regularization with Dropout and DropConnect显示文摘	Alexandras Iosifidis Anastasios Tefas Ioannis Pitas	2015	Neurocomputing2015，，162：	1
	7	Neuromorphic silicon photonics with 50 GHz tiled matrix multiplication for deep-learning applications显示文摘The explosive volume growth of deep-learning(DL)applications has triggered an era in computing,with neuromorphic photonic platforms promising to merge ultra-high speed and energy efficiency credentials with the brain-inspired computing primitives.The transfer of deep neural networks(DNNs)onto silicon photonic(SiPho)architectures requires,however,an analog computing engine that can perform tiled matrix multiplication(TMM)at line rate to support DL applications with a large number of trainable parameters,similar to the approach followed by state-of-the-art electronic graphics processing units.Herein,we demonstrate an analog SiPho computing engine that relies on a coherent architecture and can perform optical TMM at the record-high speed of 50 GHz.Its potential to support DL applications,where the number of trainable parameters exceeds the available hardware dimensions,is highlighted through a photonic DNN that can reliably detect distributed denial-of-service attacks within a data center with a Cohen’s kappa score-based accuracy of 0.636.	George Giamougiannis Apostolos Tsakyridis Miltiadis Moralis-Pegios George Mourgias-Alexandris Angelina RTotovic George Dabos Manos Kirtas Nikolaos Passalis Anastasios Tefas Dimitrios Kalavrouziotis Dimitris Syrivelis Paraskevas Bakopoulos Elad Mentovich David Lazovsky Nikos Pleros	2023	Advanced Photonics2023，5，1：	0

返回顶部每页显示：

共1页首页上一页第1页下一页末页 /1 跳转

goolge学术搜索-维普

网站首页 | 关于我们 | 联系我们 | 产品服务 | 客服中心 | 广告服务 | 版权声明 | 网站联盟 | 友情链接 | 售卡网点

版权所有© 渝B2-20050021-1　渝公网安备 50019002500403号　违法和不良信息举报中心

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费