Rethinking eliminative connectionism
Rethinking eliminative connectionism
复制标题
DOI：
10.1006/cogp.1998.0694
复制
发表时间：
1998-12-01
影响因子：
2.6
通讯作者：
Marcus, GF
中科院分区：
文献类型：
--
作者：
Marcus, GF
人类通常会将普遍的关系推广到不熟悉的实例。如果我们被告知“如果glork那么frum”和“glork”，我们可以推断出“frum”;任何作为句子主语的名字都可以作为句子的宾语出现。这些共性在语言和推理中无处不在。一种解释认为人类拥有操纵符号和变量的机制;另一种解释认为，符号操纵可以从科学理论中消除，而有利于用相互连接的节点网络来描述。这些“排除性”的联结主义模型能提供一个真正的替代方案吗？这篇文章表明，排除联结主义模型不能解释我们如何将共相扩展到任意项目。这一论点如下。首先，如果这些模型，如目前所设想的，要将共性扩展到任意实例，它们必须在训练示例的空间之外进行泛化。接下来，它表明，目前流行的消除连接模型的类不能学习扩展训练空间之外的共性。通过使用实现符号操作的体系结构，可以避免这种限制。(C)北京：科学出版社.
Humans routinely generalize universal relationships to unfamiliar instances. If we are told "if glork then frum," and "glork," we can infer "frum"; any name that serves as the subject of a sentence can appear as the object of a sentence. These universals are pervasive in language and reasoning. One account of how they are generalized holds that humans possess mechanisms that manipulate symbols and variables; an alternative account holds that symbol-manipulation can be eliminated from scientific theories in favor of descriptions couched in terms of networks of interconnected nodes. Can these "eliminative" connectionist models offer a genuine alternative? This article shows that eliminative connectionist models cannot account for how we extend universals to arbitrary items. The argument runs as follows. First, if these models, as currently conceived, were to extend universals to arbitrary instances, they would have to generalize outside the space of training examples. Next, it is shown that the class of eliminative connectionist models that is currently popular cannot learn to extend universals outside the training space. This limitation might be avoided through the use of an architecture that implements symbol manipulation. (C) 1998 Academic Press.