摘要
神经网络的存储能力一直是一个重大的缺陷,其存储主要体现在权重系数上,因此参数量一多,训练起来就十分困难。给神经网络设计一个外部关联存储器,能有效对神经网络的输入进行关联查询,并将查询的结果作为辅助输入传入到神经网络中去。此外,设计了自然语言语句的向量嵌入模型,并将模型和关联存储器集合起来形成一个自动关联语句语义向量的关联存储系统,其性能指标达到了设计要求。
The storage capacity of neural networks has always been a major flaw.Its storage is mainly reflected in the weight coefficient.Therefore,it is very difficult to train a neural network with a large amount of parameters.This paper intends to design an external associative memory for the neural network,which can effectively serve the neural network.The input is associated with the query and the result of the query is passed to the neural network as an auxiliary input.In addition,this paper designs a vector embedding model of natural language sentences,and assembles the model and associated memory to form an associative storage system with automatic association statement semantic vectors.The performance indicators of this system meet the design requirements.
作者
万迪凯
丰大军
Wan Dikai;Feng Dajun(National Computer System Engineering Research Institute of China,Beijing 100083,China)
出处
《电子技术应用》
2019年第11期10-12,16,共4页
Application of Electronic Technique
基金
核高基重大专项(2017ZX01030202)
