论文部分内容阅读
本文在 Hopfield 模型的基础上,提出了在学习过程中引入负反馈的神经网络模型。理论分析指出,由新模型构成的神经网络,提高了记忆相关图样的能力和容错能力,记忆容量也远远超过网络中神经元数目的15%。计算机模拟结果表明这些分析的正确性。本文还讨论了新模型与生物神经功能的类似性。
Based on the Hopfield model, this paper proposes a neural network model that introduces negative feedback in the learning process. Theoretical analysis shows that the neural network formed by the new model improves the capacity and fault tolerance of memory-related patterns, and the memory capacity far exceeds 15% of the number of neurons in the network. Computer simulation results show the correctness of these analyzes. This article also discusses the similarity between the new model and the biological nerve function.