Simmen Martin W, Treves Alessandro, Rolls Edmund T
a Centre for Cognitive Science , University of Edinburgh , 2 Buccleuch Place, Edinburgh EH8 9LW , UK.
b Biophysics and Cognitive Science , SISSA, via Beirut 2, 34013 Trieste , Italy.
Network. 1996;7(1):109-122. doi: 10.1080/0954898X.1996.11978657.
Networks of threshold-linear neurons have previously been introduced and analysed as distributed associative memory systems. Here, results from simulations of pattern retrieval in a large-scale, sparsely connected network are presented. The storage capacity lies near a = 0.8 and 1.2 for binary and ternary patterns respectively, in reasonable accordance with theoretical estimates. The system is capable of retrieving states strongly correlated with one of the stored patterns even when the initial state is a highly degraded version of one of these patterns. This pattern completion ability holds for an extensive number of memory patterns, up to α ≈ α/2, thereby increasing the credibility of the model as an effective associative memory.
阈值线性神经元网络此前已作为分布式联想记忆系统被引入和分析。在此，展示了大规模稀疏连接网络中模式检索的模拟结果。对于二进制和三进制模式，存储容量分别接近α = 0.8和1.2，与理论估计相当吻合。即使初始状态是其中一个存储模式的高度退化版本，该系统仍能够检索与其中一个存储模式高度相关的状态。这种模式完成能力适用于大量的记忆模式，直至α ≈ α/2，从而提高了该模型作为有效联想记忆的可信度。
