Yiming Qian

Jul 4, 2023 | onlinelibrary.wiley.com | Yiming Qian |Fengyi Zhang |zhiyong Liu

Abstract Lifelong reinforcement learning is able to continually accumulate shared knowledge by estimating the inter-task relationships based on training data for the learned tasks in order to accelerate learning for new tasks by knowledge reuse. The existing methods employ a linear model to represent the inter-task relationships by incorporating task features in order to accomplish a new task without any learning.

Jun 8, 2023 | frontiersin.org | Donglai Wei |Yiming Qian |Hongtao Wang

1. Introduction Three-dimensional segmentation of neural structures in serial scanning electron microscope (SEM) images is a fundamental task in brain connectomics studies (Kasthuri et al., 2015; Eberle et al., 2018). Although supervised deep learning methods, such as U-Net (Ronneberger et al., 2015), have become the preferred approach for image reconstruction, they rely on annotated data, which can be costly and time-consuming for large-scale image tasks.