Computer Science Department & Institute for Intelligent Systems, The University of Memphis, 365 Innovation Dr., Memphis, TN 38152, USA.
Neural Netw. 2013 Oct;46:144-53. doi: 10.1016/j.neunet.2013.05.005. Epub 2013 May 14.
Sparse distributed memory is an auto-associative memory system that stores high dimensional Boolean vectors. Here we present an extension of the original SDM, the Integer SDM that uses modular arithmetic integer vectors rather than binary vectors. This extension preserves many of the desirable properties of the original SDM: auto-associativity, content addressability, distributed storage, and robustness over noisy inputs. In addition, it improves the representation capabilities of the memory and is more robust over normalization. It can also be extended to support forgetting and reliable sequence storage. We performed several simulations that test the noise robustness property and capacity of the memory. Theoretical analyses of the memory's fidelity and capacity are also presented.
稀疏分布式记忆是一种自联想记忆系统，用于存储高维布尔向量。这里我们提出了原始 SDM 的扩展，即整数 SDM，它使用模算术整数向量而不是二进制向量。这个扩展保留了原始 SDM 的许多理想特性：自联想、内容寻址、分布式存储以及对噪声输入的鲁棒性。此外，它提高了内存的表示能力，并且在规范化方面更具鲁棒性。它还可以扩展以支持遗忘和可靠的序列存储。我们进行了几次模拟，以测试内存的噪声鲁棒性和容量。还提出了对内存的保真度和容量的理论分析。
