Rizzuto D S, Kahana M J
Volen Center for Complex Systems, Brandeis University, Waltham, MA 02454, USA.
Neural Comput. 2001 Sep;13(9):2075-92. doi: 10.1162/089976601750399317.
Hebbian heteroassociative learning is inherently asymmetric. Storing a forward association, from item A to item B, enables recall of B (given A), but does not permit recall of A (given B). Recurrent networks can solve this problem by associating A to B and B back to A. In these recurrent networks, the forward and backward associations can be differentially weighted to account for asymmetries in recall performance. In the special case of equal strength forward and backward weights, these recurrent networks can be modeled as a single autoassociative network where A and B are two parts of a single, stored pattern. We analyze a general, recurrent neural network model of associative memory and examine its ability to fit a rich set of experimental data on human associative learning. The model fits the data significantly better when the forward and backward storage strengths are highly correlated than when they are less correlated. This network-based analysis of associative learning supports the view that associations between symbolic elements are better conceptualized as a blending of two ideas into a single unit than as separately modifiable forward and backward associations linking representations in memory.
赫布异联想学习本质上是不对称的。存储从项目A到项目B的正向联想能够（在给定A的情况下）回忆起B，但（在给定B的情况下）不允许回忆起A。递归网络可以通过将A与B关联以及将B与A反向关联来解决这个问题。在这些递归网络中，正向和反向联想可以有不同的权重，以解释回忆表现中的不对称性。在正向和反向权重强度相等的特殊情况下，这些递归网络可以被建模为一个单一的自联想网络，其中A和B是单个存储模式的两个部分。我们分析了一个通用的联想记忆递归神经网络模型，并检验了它拟合关于人类联想学习的大量实验数据的能力。当正向和反向存储强度高度相关时，该模型对数据的拟合明显优于它们相关性较低时的情况。这种基于网络的联想学习分析支持这样一种观点，即符号元素之间的联想更好地被概念化为将两个想法融合为一个单一单元，而不是作为记忆中链接表征的可分别修改的正向和反向联想。
