Lifelong Machine Learning
Papers from the 2013 AAAI Spring Symposium
Eric Eaton Program Chair
Humans learn to solve increasingly complex tasks by continually building upon and refining knowledge over a lifetime of experience. This process of continual learning and transfer allows us to rapidly learn new tasks, often with very little training. Over time, it enables us to develop a wide variety of complex abilities across many domains.
Despite recent advances in transfer learning and representation discovery, lifelong machine learning remains a largely unsolved problem. Lifelong machine learning has the huge potential to enable versatile systems that are capable of learning a large variety of tasks and rapidly acquiring new abilities. These systems would benefit numerous applications, such as medical diagnosis, virtual personal assistants, autonomous robots, visual scene understanding, language translation, and many others.
Learning over a lifetime of experience involves a number of procedures that must be performed continually, including discovering representations from raw sensory data that capture higher-level abstractions; transferring knowledge learned on previous tasks to improve learning on the current task; maintaining the repository of accumulated knowledge; and incorporating external guidance and feedback from humans or other agents. Each of these procedures encompasses one or more subfields of machine learning and artificial intelligence. The papers in this report focus discussion on combining these lines of research toward lifelong machine learning.