A unified associative memory model based on external inputs of continuous recurrent neural networks

作者：Zhou, Caigen; Zeng, Xiaoqin^*; Yu, Jianjiang; Jiang, Haibo

来源：Neurocomputing, 2016, 186: 44-53.

DOI：10.1016/j.neucom.2015.12.079

• Continuous recurrent neural networks
• External inputs
• Auto-associative memory
• Hetero-associative memory
• Slope activation function

A unified associative memory model with a novel method for designing associative memories is presented in this paper. Based on continuous recurrent neural networks, bipolar patterns inputted from external can cause the output of neural networks to be memorized patterns. In the method, two conditions relevant to external inputs are derived to ensure the network states converge to a stable interval, and an exponential stable criterion is proposed for the network being a bipolar associative memory with higher recall speed. By introducing a tunable slope activation function and considering time delay, the proposed model is general and can recall the memorized patterns in auto-associative and hetero-associative way, while higher robust and more flexible memory can be obtained through the proposed method. Experimental verification demonstrates the effectiveness and generalization of the proposed method.

• 出版日期2016-4-19
• 单位河海大学; 盐城师范学院