Learning One More Thing
Sebastian Thrun, Tom M. Mitchell · 1994
Most research on machine learning has focused on scenarios in which a learner faces a single, isolated learning task. The lifelong learning frameworkassumes instead that the learner encounters a multitude of related learning tasks over its lifetime, providing the opportunity for the transfer of knowledge. This paper studies lifelong learning in the context of binary classification. It presents the invariance approach, in which knowledge is transferred via a learned model of the invariances of the domain. Results on learning to recognize objects from color images demonstrate superior generalization capabilities if invariances are learned and used to bias subsequent learning. This research is sponsored in part by the National Science Foundation under award IRI-9313367, and by the Wright Laboratory, Aeronautical Systems Center, Air Force Materiel Command, USAF, and the Advanced Research Projects Agency (ARPA) under grant number F33615-93-1-1330. Views and conclusions contained in this doc...