[logseq-plugin-git:commit] 2025-06-05T08:36:10.944Z

This commit is contained in:
2025-06-05 10:36:12 +02:00
parent b2116c22df
commit e3725ac9e7
6304 changed files with 708459 additions and 464 deletions
+4
View File
@@ -0,0 +1,4 @@
- **Transfer learning** (**TL**) is a technique in [machine learning](https://en.wikipedia.org/wiki/Machine_learning) (ML) in which knowledge learned from a task is re-used in order to boost performance on a related task. (https://en.wikipedia.org/wiki/Transfer_learning)
- For example, for [image classification](https://en.wikipedia.org/wiki/Image_classification), knowledge gained while learning to [recognize](https://en.wikipedia.org/wiki/Computer_vision#Bababoui) cars could be applied when trying to recognize trucks. This topic is related to the psychological literature on [transfer of learning](https://en.wikipedia.org/wiki/Transfer_of_learning), 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.
-
-