【转载】 迁移学习(Transfer learning),多任务学习(Multitask learning)和端到端学习(End-to-end deep learning)

--------------------- 
作者：bestrivern 
来源：CSDN 
原文：https://blog.csdn.net/bestrivern/article/details/87008263 

 

 

 

 

 

 

==========================================================

 

 

 

 

 

一.迁移学习(Transfer learning)
1.Task A and Task B has the same input x

2.You have a lot more data for Task A than Task B

3.Low level features from A could be helpful for learning B

 

 （感觉上面的第一点说的好像不太对， 所以 ，ps: point 1 is conflict with point 2, maybe point 1 should be  task A has input x  and   task B has input y,   input x  is similar with input y）

 

 

 

 

 

 

二.多任务学习(Multitask learning)
1.Training on a set of tasks that could benefit from having shared low-level features

2.Usually:Amount of data you have for each task is quite similar

3.Can train a big enough neural network to do well on all the tasks

 

 

 

 

 

 

 

 

三.端到端学习(End-to-end deep learning)
Pros:

Let the data speak
Less hand-designing of components needed

Cons: 

May need large amount of data
Excludes potentially useful hand-designed components

 

 

 

 

 

 

 

==========================================================