This paper adopts the Global Workspace Theory as a neuro-scientifically plausible theory for developing conscious cognitive architecture.The Global Workspace Theory’s compatibility with the working mechanisms underne...This paper adopts the Global Workspace Theory as a neuro-scientifically plausible theory for developing conscious cognitive architecture.The Global Workspace Theory’s compatibility with the working mechanisms underneath human brains is enhanced by the implementation of different cognitive features based on this framework.Amongst the topics in the literature for intelligent systems,we start with attention,memory and learning mechanisms,and corresponding experiments are summarized here.We also discuss how other topics of cognitive robotics could be developed based on these three basic components,and their correlations.This provides a foundation for future long-term development of cognitive architectures of cognitive robots.The research in this paper follows the incremental research pathway for the architecture implementation,which is consistent with the Biologically Inspired Cognitive Architecture roadmap.展开更多
A new framework for consciousness is introduced based upon traditional artificial neural network models. This framework reflects explicit connections between two parts of the brain: one global working memory and dist...A new framework for consciousness is introduced based upon traditional artificial neural network models. This framework reflects explicit connections between two parts of the brain: one global working memory and distributed modular cerebral networks relating to specific brain functions. Accordingly this framework is composed of three layers, physical mnemonic layer and abstract thinking layer, which cooperate together through a recognition layer to accomplish information storage and cognition using algorithms of how these interactions contribute to consciousness: (1) the reception process whereby cerebral subsystems group distributed signals into coherent object patterns; (2) the partial recognition process whereby patterns from particular subsystems are compared or stored as knowledge; and (3) the resonant learning process whereby global workspace stably adjusts its structure to adapt to patterns’ changes. Using this framework, various sorts of human actions can be explained, leading to a general approach for analyzing brain functions.展开更多
基金Supported by the European Union’s Horizon Europe research and innovation program(101120727-PRIMI).
文摘This paper adopts the Global Workspace Theory as a neuro-scientifically plausible theory for developing conscious cognitive architecture.The Global Workspace Theory’s compatibility with the working mechanisms underneath human brains is enhanced by the implementation of different cognitive features based on this framework.Amongst the topics in the literature for intelligent systems,we start with attention,memory and learning mechanisms,and corresponding experiments are summarized here.We also discuss how other topics of cognitive robotics could be developed based on these three basic components,and their correlations.This provides a foundation for future long-term development of cognitive architectures of cognitive robots.The research in this paper follows the incremental research pathway for the architecture implementation,which is consistent with the Biologically Inspired Cognitive Architecture roadmap.
文摘A new framework for consciousness is introduced based upon traditional artificial neural network models. This framework reflects explicit connections between two parts of the brain: one global working memory and distributed modular cerebral networks relating to specific brain functions. Accordingly this framework is composed of three layers, physical mnemonic layer and abstract thinking layer, which cooperate together through a recognition layer to accomplish information storage and cognition using algorithms of how these interactions contribute to consciousness: (1) the reception process whereby cerebral subsystems group distributed signals into coherent object patterns; (2) the partial recognition process whereby patterns from particular subsystems are compared or stored as knowledge; and (3) the resonant learning process whereby global workspace stably adjusts its structure to adapt to patterns’ changes. Using this framework, various sorts of human actions can be explained, leading to a general approach for analyzing brain functions.
