Goto

Collaborating Authors

The Case for Case-Based Transfer Learning

AI Magazine

Transfer learning occurs when, after gaining experience from learning how to solve source problems, the same learner exploits this experience to improve performance and learning on target problems. In transfer learning, the differences between the source and target problems characterize the transfer distance. CBR can support transfer learning methods in multiple ways. We illustrate how CBR and transfer learning interact and characterize three approaches for using CBR in transfer learning: (1) as a transfer learning method, (2) for problem learning, and (3) to transfer knowledge between sets of problems. We describe examples of these approaches from our own and related work and discuss applicable transfer distances for each.


Understanding Relevance Visa-Vis Internal Transfer

AAAI Conferences

Understanding methods of problem solving is a main goal of both Cognitive Science and Artificial Intelligence. Although general problem solvers that use weak methods have been developed, they are not sufficient for reasoning about complex problems in complicated domains. For such tasks, the search is generally intractable: the height of the search tree is determined by the complexity of the solution, and the branching factor at each level is determined by the large number of applicable operators. The principle problem is that weak methods operating on large domain theories provide the problem solver with only a very limited notion of which operators might be relevant to which goals. What is needed to solve this problem, then, is a set of learning methods that can select and retrieve past experiences that are relevant to the current goal.


Special Issue on Structured Knowledge Transfer

AI Magazine

Its goal is to capture, in a general form, the internal structure of the objects, relations, strategies, and processes used to solve tasks drawn from a source domain, and exploit that knowledge to improve performance in a target domain. A Note from the AI Magazine Editor in Chief: Part Two of the Structured Knowledge Transfer special issue will be published in the summer 2011 issue (volume 32 number 2) of AI Magazine. Articles in this issue will include: "Knowledge Transfer between Automated Planners," by Susana Fernández, Ricardo Aler, and Daniel Borrajo "Transfer Learning by Reusing Structured Knowledge," by Qiang Yang, Vincent W. Zheng, Bin Li, and Hankz Hankui Zhuo "An Application of Transfer to American Football: From Observation of Raw Video to Control in a Simulated Environment," by David J. Stracuzzi, Alan Fern, Kamal Ali, Robin Hess, Jervis Pinto, Nan Li, Tolga Könik, and Dan Shapiro "Toward a Computational Model of Transfer," by Daniel Oblinger While the field of psychology has studied transfer learning in people for many years, AI has only recently taken up the challenge. The topic received initial attention with work on inductive transfer in the 1990s, while the number of workshops and conferences has noticeably increased in the last five years. This special issue represents the state of the art in the subarea of transfer learning that focuses on the acquisition and reuse of structured knowledge.


The Case for Case-Based Transfer Learning

AI Magazine

Transfer learning occurs when, after gaining experience from learning how to solve source problems, the same learner exploits this experience to improve performance and/or learning on target problems. In transfer learning, the differences between the source and target problems characterize the transfer distance. CBR can support transfer learning methods in multiple ways. We illustrate how CBR and transfer learning interact and characterize three approaches for using CBR in transfer learning: (1) as a transfer learning method, (2) for problem learning, and (3) to transfer knowledge between sets of problems.


The Importance of Selective Knowledge Transfer for Lifelong Learning

AAAI Conferences

As knowledge transfer research progresses from single transfer to lifelong learning scenarios, it becomes increasingly important to properly select the source knowledge that would best transfer to the target task. In this position paper, we describe our previous work on selective knowledge transfer and relate it to problems in lifelong learning. We also briefly discuss our ongoing work to develop lifelong learning methods capable of continual transfer between tasks and the incorporation of guidance from an expert human user.