Learning Human Cognitive Appraisal Through Reinforcement Memory Unit

TL;DR

This paper introduces a Reinforcement Memory Unit (RMU) for recurrent neural networks that models human cognitive appraisal, improving performance in video quality assessment tasks by capturing affective responses to stimuli.

Contribution

The paper presents a novel RMU mechanism that incorporates appraisal states and reinforcement memories to enhance sequential assessment tasks in neural networks.

Findings

RMU outperforms traditional RNNs in video quality assessment.

RMU effectively models human affective responses to stimuli.

Experimental results demonstrate superior performance of RMU in relevant tasks.

Abstract

We propose a novel memory-enhancing mechanism for recurrent neural networks that exploits the effect of human cognitive appraisal in sequential assessment tasks. We conceptualize the memory-enhancing mechanism as Reinforcement Memory Unit (RMU) that contains an appraisal state together with two positive and negative reinforcement memories. The two reinforcement memories are decayed or strengthened by stronger stimulus. Thereafter the appraisal state is updated through the competition of positive and negative reinforcement memories. Therefore, RMU can learn the appraisal variation under violent changing of the stimuli for estimating human affective experience. As shown in the experiments of video quality assessment and video quality of experience tasks, the proposed reinforcement memory unit achieves superior performance among recurrent neural networks, that demonstrates the effectiveness of RMU for modeling human cognitive appraisal.