Difference between revisions of "Transfer Learning"

From
Jump to: navigation, search
Line 1: Line 1:
aka Knowledge Transfer, Learning to Learn
 
 
________________________________________________________________________________________________________________
 
 
 
[http://www.youtube.com/results?search_query=Transfer+Learning+machine+neural+network YouTube search...]
 
[http://www.youtube.com/results?search_query=Transfer+Learning+machine+neural+network YouTube search...]
 +
[http://www.google.com/search?q=Transfer+Learning+deep+machine+learning+ML ...Google search]
  
 
* [[Text Transfer Learning]]
 
* [[Text Transfer Learning]]
Line 10: 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]
 +
* [[Multitask Learning]]
  
  
 
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.
 
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.
 +
 
http://assets3.thrillist.com/v1/image/2377351/size/sk-2017_04_article_main_desktop.jpg
 
http://assets3.thrillist.com/v1/image/2377351/size/sk-2017_04_article_main_desktop.jpg
  
Transfer learning 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.  [http://machinelearningmastery.com/transfer-learning-for-deep-learning/ A Gentle Introduction to Transfer Learning for Deep Learning | Jason Brownlee - Machine Learning Mastery]
+
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.  [http://machinelearningmastery.com/transfer-learning-for-deep-learning/ A Gentle Introduction to Transfer Learning for Deep Learning | Jason Brownlee - Machine Learning Mastery]
 +
 
  
 
<youtube>Yx6Wv_SCKjI</youtube>
 
<youtube>Yx6Wv_SCKjI</youtube>

Revision as of 21:48, 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