Multi-task learning (MTL) is a subfield of machine learning in which multiple learning tasks are solved at the same time, while exploiting commonalities and differences across tasks. This can result in improved learning efficiency and prediction accuracy for the task-specific models, when compared to training the models separately.(wiki)
多任务学习 (MTL) 是机器学习的一个子领域,其中同时解决多个学习任务。与单独训练模型相比,MTL利用各任务之间的共性和差异,来提高特定任务模型的学习效率和预测准确性。 1.2 为什么采用多任务模型?