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.

Machine Understanding in Agent-Directed Simulation: State-of-the-Art and Research Directions

“…The acquired knowledge can be varied. A systematic glossary of about 60 types of machine understanding is given in another publication [27].…”

“…They are: (1) basic understanding, (2) rich understanding, (3) exploratory understanding, and (4) theory-based understanding. The details can be found there [27].…”

“…All four categories of machine understanding can be onestage or two-stage understanding as clarified by Ören et al [27].…”

“…One-stage understanding and deep understanding were elaborated for emotional intelligence by Ören et al [27]. Several machine understanding strategies can be tested and evaluated by using agent simulation, i.e.…”

“…Several machine understanding strategies can be tested and evaluated by using agent simulation, i.e. misunderstanding ( [26] and two-stage understanding [27].…”