Extension of grounding mechanism for abstract words: computational methods insights

摘要: The attempts to model cognitive phenomena effectively have split the research community in two paradigms: symbolic and connectionist. extension of grounding phenomenon for abstract words is very important social interactions robots real scenarios. This paper reviews strength connectionist methods address word problem robots. In particular, presented work focused on designing simulating robotics achieve a mechanism by using semantic network approach, as well examining utility computation same problem. Two neuro-robotics models based feed forward neural recurrent are see pros cons approach. simulation results review attributes these reveal that proposed offers solution with like high data storage capacity recall accuracy, structural integrity temporal sequence handling. Whereas, solutions give more natural this some shortcomings include combinatorial ambiguity, low rigidity. not only advancement communication system robot, also provide evidence embodied nature language.