A hierarchical attention-based neural network architecture, based on human brain guidance, for perception, conceptualisation, action and reasoning

作者：

Highlights：

•

摘要

We present a neural network software architecture, guided by that of the human and more generally primate brain, for the construction of an autonomous cognitive system (which we have named GNOSYS). GNOSYS is created so as to be able to attend to stimuli, to conceptualise them, to learn their predicted reward value and reason about them so as to attain those stimuli in the environment with greatest predicted value. We apply this software system to an embodied version in a robot, and describe the activities in the various component modules of GNOSYS, as well as the overall results. We briefly compare our system with some others proposed to have cognitive powers, and finish by discussion of future developments we propose for our system, as well as expanding on the arguments for and against our approach to creating such a software system.

论文关键词：KCL,King’s College London, UK,UTUB,University of Tubingen, Germany,FORTH,Foundation for Research & Technology – Hellas, Institute of Computer Science, Heraklion, Greece,UGDIST,University of Genoa,ZENON,Zenon Co. Ltd. Athens, Greece,FEF,frontal eye fields,IFG,inferior frontal gyrus,TEO,posterior temporal lobe,TE,temporal lobe,LIP,lateral parietal lobe,TPJ,tempero-parietal junction,SPL,superior parietal lobe,VTA,ventral tegmental area,NAcc,nucleus accumbens,OFC,orbito-frontal cortex,CTX,cortex,TD,temporal difference,LGCU,local cerebral glucose utilisation,FM,forward model,IMC,inverse model controller,Dorsal and ventral vision,Object representations,Dopamine as reward,TD learning

论文评审过程：Received 1 November 2007, Revised 9 February 2009, Accepted 17 March 2009, Available online 24 March 2009.

论文官网地址：https://doi.org/10.1016/j.imavis.2009.03.006