Qing Liu

Advances in artificial intelligence have raised a basic question about human intelligence: Is human reasoning best emulated by applying task‐specific knowledge acquired from a wealth of prior experience, or is it based on the domain‐general manipulation and comparison of mental representations? We address this question for the case of visual analogical reasoning. Using realistic images of familiar three‐dimensional objects (cars and their parts), we systematically manipulated viewpoints, part relations, and entity properties in visual analogy problems. We compared human performance to that of two recent deep learning models (Siamese Network and Relation Network) that were directly trained to solve these problems and to apply their task‐specific knowledge to analogical reasoning. We also developed a new model using part‐based comparison (PCM) by applying a domain‐general mapping procedure to learned representations of cars and their component parts. Across four‐term analogies (Experiment 1) and open‐ended analogies (Experiment 2), the domain‐general PCM model, but not the task‐specific deep learning models, generated performance similar in key aspects to that of human reasoners. These findings provide evidence that human‐like analogical reasoning is unlikely to be achieved by applying deep learning with big data to a specific type of analogy problem. Rather, humans do (and machines might) achieve analogical reasoning by learning representations that encode structural information useful for multiple tasks, coupled with efficient computation of relational similarity.

The author intends to investigate the role of social distancing laws in the new normal as well as the effectiveness of forced shift to media online learning. This research indicates that student involvement had a moderating influence during the epidemic. This study is based on social learning theory, which endeavors to emulate the behavior, perceptions, and emotions of other individuals. The data were obtained from various Chinese universities. We gathered data utilizing the stratified sample approach as well as Google Form. A total of 256 students enrolled in a variety of programs at Chinese universities completed a questionnaire for this investigation. The direct, mediating, and moderating effects of the variables were evaluated using partial least square structural equation modeling in this study, using the Smart-PLS software 3.0. According to the findings, forced shift to media online learning acts as a mediator between the lack of social interaction, perceived harm, perception of maintaining social distancing, and the law, and the effectiveness of media online learning has a significant effect on the effectiveness of media online learning. In addition, student engagement appears to be a moderator between the forced shift to media online learning and its effectiveness. A future study might concentrate on gaining a deeper understanding of the numerous online engagement-promoting behaviors. Teachers must go above and above to provide themes that enable pupils to connect while learning. Instructors and educational institutions will benefit from the research since it will allow them to define methods for boosting social interaction in online learning and analyze methods for enhancing the efficacy of media in online learning.