PROJECT TITLE :

A Probabilistic Model of Social Working Memory for Information Retrieval in Social Interactions - 2017

ABSTRACT:

Social operating memory (SWM) plays an necessary role in navigating social interactions. Inspired by studies in psychology, neuroscience, cognitive science, and Machine Learning, we have a tendency to propose a probabilistic model of SWM to mimic human social intelligence for personal information retrieval (IR) in social interactions. 1st, we tend to establish a semantic hierarchy as social long-term memory to encode personal data. Next, we propose a semantic Bayesian network as the SWM, which integrates the cognitive functions of accessibility and self-regulation. One subgraphical model implements the accessibility function to be told the social consensus about IR-based on social info concept, Clustering, social context, and similarity between persons. Beyond accessibility, yet one more layer is added to simulate the operate of self-regulation to perform the private adaptation to the consensus based on human personality. Two learning algorithms are proposed to coach the probabilistic SWM model on a raw dataset of high uncertainty and incompleteness. One is an efficient learning algorithm of Newton's methodology, and the other is a genetic algorithm. Systematic evaluations show that the proposed SWM model is able to be told human social intelligence effectively and outperforms the baseline Bayesian cognitive model. Toward real-world applications, we implement our model on Google Glass as a wearable assistant for social interaction.