首页 | 本学科首页   官方微博 | 高级检索  
   检索      


Learning to Manipulate and Categorize in Human and Artificial Agents
Authors:Giuseppe Morlino  Claudia Gianelli  Anna M Borghi  Stefano Nolfi
Institution:1. Institute of Cognitive Sciences and Technologies (ISTC) – CNR, Rome;2. Department of Computer ScienceUniversity Sapienza of Rome;3. Department of PsychologyUniversity of Bologna
Abstract:This study investigates the acquisition of integrated object manipulation and categorization abilities through a series of experiments in which human adults and artificial agents were asked to learn to manipulate two‐dimensional objects that varied in shape, color, weight, and color intensity. The analysis of the obtained results and the comparison of the behavior displayed by human and artificial agents allowed us to identify the key role played by features affecting the agent/environment interaction, the relation between category and action development, and the role of cognitive biases originating from previous knowledge.
Keywords:Embodied cognition  Categorization  Category and action learning  Shape bias  Neural networks
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号