HRL Laboratories, Malibu, CA 90265, U.S.A.
Neural Comput. 2019 May;31(5):998-1014. doi: 10.1162/neco_a_01181. Epub 2019 Mar 18.
It is still unknown how associative biological memories operate. Hopfield networks are popular models of associative memory, but they suffer from spurious memories and low efficiency. Here, we present a new model of an associative memory that overcomes these deficiencies. We call this model sparse associative memory (SAM) because it is based on sparse projections from neural patterns to pattern-specific neurons. These sparse projections have been shown to be sufficient to uniquely encode a neural pattern. Based on this principle, we investigate theoretically and in simulation our SAM model, which turns out to have high memory efficiency and a vanishingly small probability of spurious memories. This model may serve as a basic building block of brain functions involving associative memory.
目前尚不清楚联想生物记忆是如何运作的。Hopfield 网络是联想记忆的流行模型，但它们存在虚假记忆和效率低下的问题。在这里，我们提出了一种新的联想记忆模型，克服了这些缺陷。我们称这个模型为稀疏联想记忆（SAM），因为它是基于从神经模式到模式特定神经元的稀疏投影。已经证明这些稀疏投影足以唯一地对神经模式进行编码。基于这一原理，我们从理论和模拟两个方面研究了我们的 SAM 模型，结果表明它具有很高的存储效率和极小的虚假记忆概率。这个模型可能是涉及联想记忆的大脑功能的基本构建块。
