Can machines think? Since Alan Turing asked this question in 1950, nobody is able to give a direct answer, due to the lack of solid mathematical foundations for general intelligence. In this paper, we introduce a categorical framework towards this goal, consisting of four components: the sensor, world category, planner with objectives, and actor. By leveraging category theory, many important notions in general intelligence can be rigorously defined and analyzed. For instance, we introduce the concept of self-state awareness as a categorical analogy for self-consciousness and provide algorithms for learning and evaluating it. For communication with other agents, we propose to use diagrams that capture the exact representation of the context, instead of using natural languages. Additionally, we demonstrate that by designing the objectives as the output of function over self-state, the model's human-friendliness is guaranteed. Most importantly, our framework naturally introduces various constraints based on categorical invariance that can serve as the alignment signals for training a model that fits into the framework.
翻译:自阿兰·图灵在1950年提出这一问题以来,没有人能够直接回答这个问题,因为一般情报缺乏坚实的数学基础。在本文中,我们引入了实现这一目标的绝对框架,由四个组成部分组成:传感器、世界类别、目标规划者和行为者。通过利用分类理论,一般情报中的许多重要概念可以严格界定和分析。例如,我们引入自我意识概念,作为自我意识的绝对类比,并提供学习和评价的算法。关于与其他代理人的沟通,我们提议使用图表,说明背景的确切表现,而不是使用自然语言。此外,我们通过将目标设计为自我状态功能的输出,模型的人类友好性得到了保障。最重要的是,我们的框架自然引入了各种基于绝对的无差别的制约,可以作为匹配信号,用于培训适合框架的模型。</s>