COGVIEW INTELNET: Nuanced energy-based knowledge representation and integrated cognitive-conceptual framework for realistic culture, values, and concept-affected systems simulation

摘要

An increasingly important AI frontier is the ability to represent worldviews, culture, values, and other nuanced structures, and to simulate the effects of these on perception, emotion/affect, judgment, and opinion formation. Such information, however, is notably difficult to model and represent, due to its fine-grained, diffuse nature. Reasoning is also highly challenging in these domains. This paper presents a novel ‘Energy-Based’ Knowledge Representation formalism (INTELNET) ideal for modeling, fusing, and reasoning about nuanced semantics, cultures, affects, and worldviews. It then introduces the integrated COGVIEW conscious/unconscious psychological simulation framework operating on top of INTELNET and advances a detailed example within the suicide terrorism domain. Applications include intelligent reasoning systems, humanitarian missions, cultural simulations, knowledge engineering, language processing, anti-discrimination and prejudice reduction, terrorism reduction, and norm change efforts, among others.