Wiki › Technique

Transfer learning

Article
From Chaipat's knowledge graph
No article has been written for this page yet; it is generated from the knowledge graph.
About Transfer learning · from Wikipedia

Transfer learning (TL) is a technique in machine learning (ML) in which knowledge learned from a task is re-used in order to boost performance on a related task. For example, for image classification, knowledge gained while learning to recognize cars could be applied when trying to recognize trucks. This topic is related to the psychological literature on transfer of learning, although practical ties between the two fields are limited. Reusing or transferring information from previously learned tasks to new tasks has the potential to significantly improve learning efficiency.

Summary from Wikipedia ↗, CC BY-SA 4.0.
  • Handwritten digit OCR Oct 2024
    The notebooks compare training set-ups on the same task: a CNN trained for 50 and for 200 epochs; the same with early stopping, which ends training when validation stops improving; transfer learning from VGG16, a network pre-trained on ImageNet, including a variant with a higher learning rate; a notebook comparing the results.
Handwritten digit OCR