Agents with four categories of understanding abilities and their role in two-stage (deep) emotional intelligence simulation

Abstract

Understanding is the essence of any intelligent system. We revise our four machine understanding paradigms which are: (i) basic understanding, (ii) rich understanding, (iii) exploratory understanding, and (iv) theory-based understanding; and we elaborate on the first two of them. We then introduce the concept of two-stage (or deep) machine understanding which provides descriptive understandings, as well as evaluations of these understandings. After a brief systematization of emotions, we cover the following paradigms for agents with two-stage (deep) understanding abilities for emotional intelligence simulation: (i) basic understanding, (ii) rich-understanding, and (iii) switchable understanding.