This paper updates the cognitive model, firstly by creating two systems and then unifying them over the same structure. It represents information at the semantic level only, where labelled patterns are aggregated into a 'type-set-match' form. It is described that the aggregations can be used to match across regions with potentially different functionality and therefore give the structure a required amount of flexibility. The theory is that if the model stores information which can be transposed in consistent ways, then that will result in knowledge and some level of intelligence. As part of the design, patterns have to become distinct and that is realised by unique paths through shared aggregated structures. An ensemble-hierarchy relation also helps to define uniqueness through local feedback that may even be an action potential. The earlier models are still consistent in terms of their proposed functionality, but some of the architecture boundaries have been moved to match them up more closely. After pattern optimisation and tree-like aggregations, the two main models differ only in their upper, more intelligent level. One provides a propositional logic for mutually inclusive or exclusive pattern groups and sequences, while the other provides a behaviour script that is constructed from node types. It can be seen that these two views are complimentary and would allow some control over behaviours, as well as memories, that might get selected.
翻译:本文更新了认知模型, 首先通过创建两个系统, 然后将它们统一到同一结构中。 它只代表语义层面的信息, 标记的图案将集成为“ 类型设置匹配” 的形式。 描述中, 汇总可以用来匹配不同区域的潜在功能, 从而给结构带来必要的灵活性。 理论是, 如果模型存储的信息能够以一致的方式被移植, 那么这将导致知识和某种程度的智能。 作为设计的一部分, 模式必须变得独特, 并且通过共享的聚合结构的独特路径实现。 组合式等级关系还有助于通过地方反馈来定义独特性, 甚至可能是一种行动潜力。 早期的模型在拟议功能方面仍然是一致的, 但有些结构界限已经移动到更接近它们。 在模式优化和树类集合之后, 两种主要模型只在高层次和智能层次上产生差异。 其中一个模型为相互包容或排他性模式组合和序列提供了一种建议性逻辑, 而另一个模型则提供了一种行为脚本, 因为它是来自一种不理解的缩略图。 它可以使两种理解得到两种理解。