Difference between revisions of "Transfer Learning"

From
Jump to: navigation, search
Line 7: Line 7:
 
* [[Style Transfer]]
 
* [[Style Transfer]]
 
* [http://hal.archives-ouvertes.fr/hal-01575126/document A Review of Transfer Learning Algorithms | Mohsen Kaboli]
 
* [http://hal.archives-ouvertes.fr/hal-01575126/document A Review of Transfer Learning Algorithms | Mohsen Kaboli]
 +
* [[Few Shot Learning]]
 
* [[Multitask Learning]]
 
* [[Multitask Learning]]
  

Revision as of 22:40, 3 January 2019

YouTube search... ...Google search


Who is the predator? Who is the prey? Have you ever seen a live dinosaur? Not ever seeing a live dinosaur and knowing the predator/prey answers is 'transfer' learning.

sk-2017_04_article_main_desktop.jpg

Transfer learning (aka Knowledge Transfer, Learning to Learn) is a machine learning technique where a model trained on one task is re-purposed on a second related task. Transfer learning is an optimization that allows rapid progress or improved performance when modeling the second task. A Gentle Introduction to Transfer Learning for Deep Learning | Jason Brownlee - Machine Learning Mastery