Transfer+Learning+-+Machine+Learning%27s+Next+Frontier.pdf

立即下载 作者: 甲基蓝
上传时间: 2025-04-04
关键词: Learning Transfer representation bu 机器 training. countered en erent di
大小 12.1 MB
描述
21 Mar 2017
Table of contents:
Transfer Learning - Machine Learning's
Next Frontier 
What is Transfer Learning?
Why Transfer Learning Now?
A Denition of Transfer Learning
Transfer Learning Scenarios
Applications of Transfer Learning
Learning from simulations
Adapting to new domains
Transferring knowledge across languages
Transfer Learning Methods
Using pre-trained CNN features
Learning domain-invariant representations
Making representations more similar
Confusing domains
Related Research Areas
In recent years, we have become increasingly good at training deep neural networks to learn a
very accurate mapping from inputs to outputs, whether they are images, sentences, label
predictions, etc. from large amounts of labeled data.
What our models still frightfully lack is the ability to generalize to conditions that are dierent
from the ones encountered during training. When is this necessary? Every time you apply your
model not to a carefully constructed dataset bu
目录
Learning/Transfer/representation/bu/机器/training./countered/en/erent/di/ Learning/Transfer/representation/bu/机器/training./countered/en/erent/di/