摘要
基于动态路由规则的胶囊网络模型是近年来新提出的神经网络模型,被认为可能成为下一代重要的神经网络模型。近年来,众多研究表明胶囊网络具备更好地拟合特征的能力,但是由于计算开销巨大,网络模型始终无法适应大数据集的要求。减少计算开销成为了胶囊网络的研究热点。减少胶囊网络的计算开销通常有两种方式,即优化胶囊法和优化路由法。优化胶囊法通常以应用目的为驱动,设计专门针对某种分类任务的网络模型;优化路由法则更具一般性,从算法角度提升胶囊网络的性能。
Recently capsule network with dynamic routing was the new neural network model which was considered a significant model in next generation. In recent years, much research evidenced capsule network exceptional ability to fit features. But the high computational overhead made it unable to fit complex and large datasets. Consequently, reducing computational became a research hotspot. There were two methods, including optimized capsule and optimized routing, to solve the issue. Optimized capsule was usually driven by application purpose which was designed as a model of specific classification tasks. And optimized routing was the way to improve the performance of the model from an algorithmic perspective.
作者
杨巨成
韩书杰
毛磊
代翔子
陈亚瑞
YANG Jucheng;HAN Shujie;MAO Lei;DAI Xiangzi;CHEN Yanii(College of Anificial Intelligence,Tianjin University of Science and Technology,Tianjin 300457,China)
出处
《山东大学学报（工学版）》
CAS
CSCD
北大核心
2019年第6期1-10,共10页
Journal of Shandong University（Engineering Science）
关键词
胶囊网络
神经网络
动态路由
优化胶囊
优化路由
capsule network
neural network
dynamic routing
optimized capsule
optimized routing
