What is Transfer Learning on Machine Learning
Machine learning methods work well only under a common assumption:
The training and test data are drawn from the same feature space and the same distribution. When the distribution changes, most statistical models need to be rebuilt from scratch using newly collected training data.
It is expensive or impossible to recollect the needed training data and rebuild the models.
Knowledge transfer or transfer learning between task domains would be desirable.
Transfer the classification knowledge into the new domain.
Different learning processes between (a) traditional machine learning and (b) transfer learning.
OVERVIEW
This paper focus on transfer learning for classification, regression, and clustering problems that are related more closely to data mining tasks.
In transfer learning, we have the following three main research issues:
1) what to transfer,
2) how to transfer,
3) when to transfer.
“What to transfer” asks which part of knowledge can be transferred across domains or tasks.
“When to transfer” asks in which situations, transferring skills should be done.
Most current work on transfer learning focuses on
“What to transfer” and “How to transfer”.
“What to transfer” has four cases
1.
Context can be referred to as
instance-based transfer learning
2.
Feature-representation-
transfer approach
3.
Parameter-transfer
approach
4.
The relational knowledge-
transfer problem
Below are table and overview of Transfer Learning setting.
The detail are in the reference paper and it is too much .
Different Settings of Transfer Learning
An overview of different settings of transfer.
沒有留言:
張貼留言