- 1、本文档共32页,可阅读全部内容。
- 2、有哪些信誉好的足球投注网站(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
Large Scale Deep Learning
Large Scale Deep Learning
Quoc V. Le
Google CMU
Deep Learning
?? Google is using Machine Learning
?? Machine Learning is difficult
?? Requires domain knowledge from human experts
Deep Learning:
?? Great performances for many problems
?? Works well with a large amount of data
?? Requires less domain knowledge
Focus:
?? Scale deep learning to bigger models and bigger problems
Quoc V. Le
Deep Learning
?? Google is using Machine Learning
?? Machine Learning is difficult
?? Requires domain knowledge from human experts
Deep Learning:
?? Great performances for many problems
?? Works well with a large amount of data
?? Requires less domain knowledge
Focus:
?? Scale deep learning to bigger models and bigger problems
Quoc V. Le
Quoc V. Le
What is Deep Learning?
Quoc V. Le
x
v = g(B u)
…
A
(images, audio, texts, etc.)
u = g(A x)
What is Deep Learning?
B
Quoc V. Le
x
v = g(B u)
…
A
(images, audio, texts, etc.)
u = g(A x)
What is Deep Learning?
B
Quoc V. Le
…
Pixels
High-level features by Deep Learning
Edge detectors
Face detector, Cat detector
Model
Training Data
Quoc V. Le
Google’s DistBelief
Goal: Train deep learning on many
machines
Model: A multiple layered architecture
Forward pass to compute the
features
Backward pass to compute the
gradient
Model
DistBelief distributes a model across
multiple machines and multiple cores.
Training Data
Machine (Model Partition)
Quoc V. Le
Model partition with DistBelief
Model
Machine (Model Partition)
Core
Training Data
Quoc V. Le
DistBelief distributes a model across
multiple machines and cores.
Model partition with DistBelief
Model
Training Data
Stochastic Gradient Descent (SGD)
Model parameters are partitioned
Can use up to 1000 cores
Quoc V. Le
Model partition with DistBelief
Model
Training Data
But training is still slow on large data sets
Can we add more parallelism?
Idea: Train multiple models on different
partition
您可能关注的文档
- Homotopy classes of maps between Knaster continua.pdf
- Horizontally homothetic submersions and nonnegative curvature.pdf
- hormone release.pdf
- hospital cleaner.pdf
- Hot Molecular Cores and High-Mass Star Formation.pdf
- HOW TO EARN MONEY.ppt
- how did chinese new year come.ppt
- How Far and How Much Further.pdf
- How Sensitive Are Weak Lensing Statistics to Dark Energy Content.pdf
- how to apply analytics where they will yield the greatest results.pdf
文档评论(0)