首页>
外国专利>
SYSTEM AND METHOD FOR PSEUDO-TASK AUGMENTATION IN DEEP MULTITASK LEARNING
SYSTEM AND METHOD FOR PSEUDO-TASK AUGMENTATION IN DEEP MULTITASK LEARNING
展开▼
机译:深多任务学习中伪任务增强的系统和方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
A multi-task (MTL) process is adapted to the single-task learning (STL) case, i.e., when only a single task is available for training. The process is formalized as pseudo-task augmentation (PTA), in which a single task has multiple distinct decoders projecting the output of the shared structure to task predictions. By training the shared structure to solve the same problem in multiple ways, PTA simulates the effect of training towards distinct but closely-related tasks drawn from the same universe. Training dynamics with multiple pseudo-tasks strictly subsumes training with just one, and a class of algorithms is introduced for controlling pseudo-tasks in practice.
展开▼