A Hierarchical Emotion Regulated Sensorimotor Model: Case Studies
This work addresses the challenge of modeling emotion-driven behavior in AI systems, but it appears incremental as it builds on existing hierarchical and perception-action models.
The paper tackled the problem of how internal states like emotion regulate sensorimotor behaviors in cognitive agents, proposing a hierarchical model based on Bayesian frameworks and testing it with a novel recurrent neural network (RNNPB) in two case studies, though no concrete numerical results were provided.
Inspired by the hierarchical cognitive architecture and the perception-action model (PAM), we propose that the internal status acts as a kind of common-coding representation which affects, mediates and even regulates the sensorimotor behaviours. These regulation can be depicted in the Bayesian framework, that is why cognitive agents are able to generate behaviours with subtle differences according to their emotion or recognize the emotion by perception. A novel recurrent neural network called recurrent neural network with parametric bias units (RNNPB) runs in three modes, constructing a two-level emotion regulated learning model, was further applied to testify this theory in two different cases.