Ryan S W, Andreae J H
Dept. of Electr. and Electron. Eng., Canterbury Univ., Christchurch.
IEEE Trans Neural Netw. 1995;6(1):125-30. doi: 10.1109/72.363443.
A parallel associative memory first proposed by Kanerva (1988) is discussed. The major appeal of this memory is its ability to be trained very rapidly. A discrepancy between Kanerva's theoretical calculation of capacity and the actual capacity is demonstrated experimentally and a corrected theory is offered. A modified method of reading from memory is suggested which results in a capacity nearly the same as that originally predicted by Kanerva. The capacity of the memory is then analyzed for a different method of writing to memory. This method increases the capacity of the memory by an order of magnitude. A further modification is suggested which increases the learning rate of this method.
本文讨论了卡内尔瓦（1988年）首次提出的并行联想存储器。这种存储器的主要吸引力在于其能够非常快速地进行训练。通过实验证明了卡内尔瓦容量理论计算与实际容量之间的差异，并提出了修正理论。建议了一种改进的从存储器读取的方法，其结果是容量几乎与卡内尔瓦最初预测的相同。然后针对不同的写入存储器的方法分析了存储器的容量。这种方法将存储器的容量提高了一个数量级。还提出了进一步的改进，提高了该方法的学习率。
