AUTHOR=Zhang Zhengchao , Zhou Lianke , Wu Yuyang , Wang Nianbin TITLE=The meta-learning method for the ensemble model based on situational meta-task JOURNAL=Frontiers in Neurorobotics VOLUME=Volume 18 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1391247 DOI=10.3389/fnbot.2024.1391247 ISSN=1662-5218 ABSTRACT=Meta-learning methods have been widely used to solve the problem of few-shot learning.Generally, meta-learners are trained on a variety of tasks and then generalized to novel tasks.However, existing meta-learning methods do not consider the relationship between meta-tasks and novel tasks during meta-training period, so that initial models of the meta-learner provide less useful meta-knowledge for the novel tasks.This leads to weak generalization ability on novel tasks. At the same time, different initial models contain different meta-knowledge, which leads to certain differences in the learning effect of novel tasks during the meta-testing period.Therefore, this paper puts forward a meta-optimization method based on situational meta-task construction and cooperation of multiple initial models. Firstly, during the meta-training period, a method of constructing situational meta-task is proposed, and the selected candidate task sets provide more effective meta-knowledge for novel tasks.Then, during the meta-testing period, an ensemble model method based on meta-optimization is proposed to minimize the loss of inter-model cooperation in prediction, so that multiple models cooperation can realize the learning of novel tasks.The above mentioned methods are applied to popular few-shot character dataset and image recognition datasets. Furthermore, the experiment results indicate that the proposed method achieves good effects in few-shot classification tasks.