期刊
JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE
卷 16, 期 3, 页码 125-144出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/09528130410001712862
关键词
analogy; analogical mapping; reasoning; connectionist symbol processing; distributed representations; representation of structure; codevector; sparse coding; binary coding; binding; associative-projective neural networks; APNN
This paper presents some techniques for analogical mapping using associative-projective neural networks (APNNs). Sparse binary distributed representations of constant high dimensionality are constructed on-the-fly for hierarchical structures of various complexity. Such representations encode both surface and structural similarity of analogical episodes. The introduced mapping approaches are illustrated using test analogies.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据