Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture
Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture
复制标题
DOI：
10.1080/095400998116549
复制
发表时间：
1998-06-01
影响因子：
5.3
通讯作者：
Phillips, S
中科院分区：
文献类型：
--
作者：
Phillips, S
人类的认知被认为是系统的：认知能力概括为结构上相关的行为。联结主义的认知理论化方法因未能解释系统性而受到强烈批评。尽管证明了泛化，但我表明，两个广泛使用的网络(前馈和递归)在局部输入/输出表示的条件下不支持系统性。对于系统性的联结主义解释，这些结果留下了两个选择：(1)在局部输入/输出表示下开发能够系统性的模型，或者(2)证明基于相似性的(非局部)分量表示的选择对于系统性是充分的。
Human cognition is said to be systematic: cognitive ability generalizes to structurally related behaviours. The connectionist approach to cognitive theorizing has been strongly criticized for its failure to explain systematicity. Demonstrations of generalization notwithstanding, I show that two widely used networks (feedforward and recurrent) do not support systematicity under the condition of local input/output representations. For a connectionist Explanation of systematicity these results leave two choices: either (1) develop models capable of systematicity, under local input/output representations or (2) justify the choice of similarity-based (non-local) component representations sufficient for systematicity.