Transfer learning

<p>Transfer learning (TL) is a technique in <a href="/facts/Machine_learning/e0w0XJTu">machine learning</a> (ML) in which knowledge learned from a task is re-used in order to boost performance on a related task. For example, for <a href="/facts/Computer_vision/Tl2Yyk66">image classification</a>, knowledge gained while learning to <a href="/facts/Computer_vision/Tl2Yyk66">recognize</a> cars could be applied when trying to recognize trucks. This topic is related to the psychological literature on <a href="/facts/Transfer_of_learning/BwfSv1Ew">transfer of learning</a>, although practical ties between the two fields are limited. Reusing/transferring information from previously learned tasks to new tasks has the potential to significantly improve learning efficiency.
</p><p>Since transfer learning makes use of training with multiple objective functions it is related to <a href="/facts/Cost-sensitive_machine_learning/y5oV0r66">cost-sensitive machine learning</a> and <a href="/facts/Multi-objective_optimization/1Hb4gjGJ">multi-objective optimization</a>.
</p>

Transfer learning open-in-new

Transfer learning