Model construction in general intelligence

作者: Stefan Schneider , Ahmed M. H. Abdel-Fattah , Benjamin Angerer , Felix Weber

DOI: 10.1007/978-3-642-39521-5_12

关键词: Protocol (object-oriented programming)Structure (mathematical logic)AnalogyConceptual blendingComputer scienceCategorizationArtificial intelligenceConcept learningConstruct (python library)Adaptation (computer science)

摘要: In this conceptual paper we propose a shift of perspective for parts AI --- from search to model construction. We claim that humans construct problem situation consisting only few, hierarchically structured elements. A allows selectively explore possible continuations and solutions, the flexible instantiation adaptation concepts. underpin our claims by results two protocol studies on problem-solving imagery inductive learning an algorithmic structure. suggest fresh look into small-scale construction processes execute would further ideas in categorization, analogy, concept formation, blending, related fields AI.

参考文章(1)
John E. Laird, Extending the Soar Cognitive Architecture artificial general intelligence. pp. 224- 235 ,(2008) , 10.21236/ADA473738