CONNECTIONIST MODELS OF RECOGNITION MEMORY - CONSTRAINTS IMPOSED BY LEARNING AND FORGETTING FUNCTIONS
CONNECTIONIST MODELS OF RECOGNITION MEMORY - CONSTRAINTS IMPOSED BY LEARNING AND FORGETTING FUNCTIONS
复制标题
DOI：
10.1037/0033-295x.97.2.285
复制
发表时间：
1990-04-01
影响因子：
5.4
通讯作者：
RATCLIFF, R
中科院分区：
文献类型：
--
作者：
RATCLIFF, R
基于使用反向传播学习规则的编码器模型，评估了多层连接主义记忆模型。这些模型被应用于标准的识别记忆程序，在该程序中，项目被顺序学习，然后测试其保持能力。这些模型中的顺序学习导致了两个主要问题。首先，随着新信息的学习，学得好的信息很快就会被遗忘。第二，学习项目和新项目之间的区别要么减少，要么作为学习的函数不是单调的。为了解决这些问题，研究了多层模型中的网络操纵和多层模型的几种变体，包括具有预学习记忆的模型和上下文模型，但都没有解决问题。所讨论的问题限制了连接主义模型应用于人类记忆，以及在学习过程中要学习的信息并非全部可用的任务中。
Multilayer connectionist models of memory based on the encoder model using the backpropagation learning rule are evaluated. The models are applied to standard recognition memory procedures in which items are studied sequentially and then tested for retention. Sequential learning in these models leads to 2 major problems. First, well-learned information is forgotten rapidly as new information is learned. Second, discrimination between studied items and new items either decreases or is nonmonotonic as a function of learning. To address these problems, manipulations of the network within the multilayer model and several variants of the multilayer model were examined, including a model with prelearned memory and a context model, but none solved the problems. The problems discussed provide limitations on connectionist models applied to human memory and in tasks where information to be learned is not all available during learning.