摘要
自适应模式识别系统具有大规模并行分布处理能力、通用性和自适应性 ,因而显示了巨大的潜力 .但由于其结构的原因 ,系统性能受到了一定的限制 .利用P .Kanerva提出的稀疏分布存贮原理对自适应模式识别系统进行改进 ,提出了一种新的系统模型 ,并就新系统的工作过程和主要特点作了较为详尽的叙述 .
Adaptive pattern recognition system (WISARD) has found extensive applications in various areas because of its massive parallel distributed processing ability, versatility and self adaptability. However, it has the weakness in the system structure. In this paper,a WISARD system was improved with the principle of the sparse distributed memory(SDM), proposed by P.kanerva. The main feature and work process of the new system has been described in detail.
关键词
稀疏分布存贮
神经网络
自适应模式识别系统
pattern recognition
sparse distributed memory
neural network
self adaptabilit$
