The power of joint learning n multiple tasks arises from the transfer of relevant knowledge across said tasks, especially from information-rich tasks to information-poor ones. Lifelong learning, on the other hand, provides an efficient way to learn new tasks faster by utilizing the knowledge learned from the previous tasks and prevent catastrophic forgetting orignificantly degrading performance on the old tasks.Despite severaladvantages on learning from related tasks,it poses considerable challenges interms of effectiveness by minimizing prediction errors for all tasks and overall computational tractability for real-time performance, especially when the number of tasks is large.
In contrast, human beings seem natural in accumulating and retaining the knowledge from the past and leverage this knowledge to acquire new skills and solve new problems efficiently. In this thesis, we propose simple and efficient algorithms for multitask and lifelong learning to address the aforementioned challenges. The primary focus of this thesis is to scale the multitask and lifelong learning to practical applications where both the tasks and the examples of the tasks arrive in an online fashion.
Jaime Carbonell (Chair)
Avrim Blum (Toyota Technical Institute at Chicago)