Baars Bernard J, Franklin Stan
The Neurosciences Institute, San Diego, CA 92121, USA; 3616 Chestnut St., Apt. 3, Lafayette, CA 94549, USA.
Neural Netw. 2007 Nov;20(9):955-61. doi: 10.1016/j.neunet.2007.09.013. Epub 2007 Sep 18.
While neural net models have been developed to a high degree of sophistication, they have some drawbacks at a more integrative, "architectural" level of analysis. We describe a "hybrid" cognitive architecture that is implementable in neuronal nets, and which has uniform brainlike features, including activation-passing and highly distributed "codelets," implementable as small-scale neural nets. Empirically, this cognitive architecture accounts qualitatively for the data described by Baars' Global Workspace Theory (GWT), and Franklin's LIDA architecture, including state-of-the-art models of conscious contents in action-planning, Baddeley-style Working Memory, and working models of episodic and semantic longterm memory. These terms are defined both conceptually and empirically for the current theoretical domain. The resulting architecture meets four desirable goals for a unified theory of cognition: practical workability, autonomous agency, a plausible role for conscious cognition, and translatability into plausible neural terms. It also generates testable predictions, both empirical and computational.
虽然神经网络模型已经发展到了高度复杂的程度，但在更综合的“架构”分析层面上，它们存在一些缺陷。我们描述了一种“混合”认知架构，它可以在神经元网络中实现，并且具有统一的类脑特征，包括激活传递和高度分布式的“微处理器”，可作为小规模神经网络来实现。从经验上看，这种认知架构定性地解释了由巴尔斯的全局工作空间理论（GWT）和富兰克林的LIDA架构所描述的数据，包括行动规划中意识内容的最新模型、巴德利式工作记忆以及情景和语义长期记忆的工作模型。这些术语在当前理论领域中从概念和经验两方面进行了定义。由此产生的架构满足了统一认知理论的四个理想目标：实际可操作性、自主能动性、意识认知的合理作用以及可转化为合理的神经学术语。它还产生了可检验的预测，包括经验性预测和计算性预测。
