Some approaches to analogical mapping with structure-sensitive distributed representations

作者: Dmitri A. Rachkovskij

DOI: 10.1080/09528130410001712862

关键词:

摘要: 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 hierarchical structures various complexity. Such encode both surface and structural similarity episodes. The introduced approaches illustrated test analogies.

参考文章(27)
Pentti Kanerva, Binary Spatter-Coding of Ordered K-Tuples international conference on artificial neural networks. pp. 869- 873 ,(1996) , 10.1007/3-540-61510-5_146
Ross W. Gayler, Roger Wales, Connections, Binding, Unification and Analogical Promiscuity New Bulgarian University, Sofia. ,(1998)
Jordan B. Pollack, Recursive distributed representations Artificial Intelligence. ,vol. 46, pp. 77- 105 ,(1990) , 10.1016/0004-3702(90)90005-K
John E. Hummel, Keith J. Holyoak, Distributed representations of structure: A theory of analogical access and mapping. Psychological Review. ,vol. 104, pp. 427- 466 ,(1997) , 10.1037/0033-295X.104.3.427
Brian H. Ross, Distinguishing Types of Superficial Similarities: Different Effects on the Access and Use of Earlier Problems Journal of Experimental Psychology: Learning, Memory and Cognition. ,vol. 15, pp. 456- 468 ,(1989) , 10.1037/0278-7393.15.3.456
Dedre Gentner, Structure‐Mapping: A Theoretical Framework for Analogy* Cognitive Science. ,vol. 7, pp. 155- 170 ,(1983) , 10.1016/S0364-0213(83)80009-3
Dedre Gentner, Arthur B. Markman, Structure mapping in analogy and similarity. American Psychologist. ,vol. 52, pp. 45- 56 ,(1997) , 10.1037/0003-066X.52.1.45