Deeplearning4j

来自开放百科 - 灰狐
(版本间的差异)
跳转到: 导航, 搜索
(图集)
 
(未显示1个用户的19个中间版本)
第1行: 第1行:
 +
deeplearning4j(DL4j)
 +
 +
[[文件:DL4J-logo.png|right|DL4J]]
 +
 +
==简介==
 +
Eclipse Deeplearning4j
 +
 
deeplearning4j:开源(Apache v2)[[Artificial neural network|神经网络]]平台,基于 [[Apache Hadoop]], [[Apache Spark]] 构建,为 [[Java]], [[Scala]] & [[Clojure]] 编程语言提供的[[deep learning|深度学习]]库。
 
deeplearning4j:开源(Apache v2)[[Artificial neural network|神经网络]]平台,基于 [[Apache Hadoop]], [[Apache Spark]] 构建,为 [[Java]], [[Scala]] & [[Clojure]] 编程语言提供的[[deep learning|深度学习]]库。
 +
 +
 +
==新闻==
 +
*2017 年 10 月,Skymind 加入了 Eclipse 基金会,并且将 DL4J 贡献给开源 Java Enterprise Edition 生态系统。
 +
 +
==指南==
 +
*[https://developer.ibm.com/zh/technologies/artificial-intelligence/articles/cc-get-started-deeplearning4j/ Deeplearning4j 入门]
 +
 +
git clone https://github.com/eclipse/deeplearning4j-examples
 +
cd deeplearning4j-examples
 +
mvn clean install
 +
使用 [[IntelliJ IDEA]] 打开项目,[http://deeplearning4j.org/quickstart.html 完成DL4J第一次体验]。
  
 
==应用场景==
 
==应用场景==
第13行: 第32行:
 
==DL4J[http://deeplearning4j.org/neuralnet-overview 神经网络]==
 
==DL4J[http://deeplearning4j.org/neuralnet-overview 神经网络]==
 
[http://deeplearning4j.org/neuralnetworktable.html 如何选择神经网络]
 
[http://deeplearning4j.org/neuralnetworktable.html 如何选择神经网络]
*[http://deeplearning4j.org/zh-restrictedboltzmannmachine.html 受限玻尔兹曼机]
+
*[https://deeplearning4j.org/cn/restrictedboltzmannmachine 受限玻尔兹曼机]
*[http://deeplearning4j.org/zh-convolutionalnets.html 卷积网络](图像)
+
*[https://deeplearning4j.org/cn/convolutionalnets 卷积网络](图像)
*[http://deeplearning4j.org/usingrnns.html 递归网络]/[http://deeplearning4j.org/lstm.html LSTMs](时间序列和传感器数据)
+
*[https://deeplearning4j.org/cn/lstm 递归网络/LSTMs](时间序列和传感器数据)
*[https://github.com/deeplearning4j/deeplearning4j/blob/master/deeplearning4j-core/src/main/java/org/deeplearning4j/nn/layers/feedforward/autoencoder/recursive/RecursiveAutoEncoder.java 递归自动编码器]
+
*[https://deeplearning4j.org/cn/deepbeliefnetwork 深度置信网络]
*[http://deeplearning4j.org/deepbeliefnetwork.html 深度置信网络]
+
*[https://deeplearning4j.org/cn/deepautoencoder 深度自动编码器](问答、数据压缩)
*[http://deeplearning4j.org/deepautoencoder.html 深度自动编码器](问-答/数据压缩)
+
*[https://deeplearning4j.org/cn/usingrnns 递归神经传感器网络](场景、分析)
*递归神经传感器网络(场景、分析)
+
*[https://deeplearning4j.org/cn/stackeddenoisingautoencoder 堆叠式降噪自动编码器]
*[http://deeplearning4j.org/stackeddenoisingautoencoder.html 堆叠式降噪自动编码器]
+
*[https://github.com/deeplearning4j/rl4j 深度增强学习]
  
 
==为何选择DL4J==
 
==为何选择DL4J==
第30行: 第49行:
 
*[[ND4J]]:线性代数库,较[[Numpy]]快一倍
 
*[[ND4J]]:线性代数库,较[[Numpy]]快一倍
 
*[http://deeplearning4j.org/documentation 文档全面、有深度、多语言]
 
*[http://deeplearning4j.org/documentation 文档全面、有深度、多语言]
 
==指南==
 
  
 
==推荐引擎==
 
==推荐引擎==
第37行: 第54行:
  
 
==[[Apache Spark|Spark]]==
 
==[[Apache Spark|Spark]]==
*[http://deeplearning4j.org/spark.html Deeplearning4j on Spark]
+
*[https://deeplearning4j.org/cn/spark 基于Spark的Deeplearning4j]
*[http://deeplearning4j.org/iterativereduce Iterative Reduce With DL4J on Hadoop and Spark]
+
*[https://deeplearning4j.org/cn/iterativereduce DL4J与基于Hadoop和Spark的迭代式归纳]
 
*[http://deeplearning4j.org/spark-fast-native-binaries.html How to Speed Up Spark With Native Binaries and OpenBlas]
 
*[http://deeplearning4j.org/spark-fast-native-binaries.html How to Speed Up Spark With Native Binaries and OpenBlas]
 +
 +
==Kotlin==
 +
[https://deeplearning4j.org/kotlin Using Deeplearning4j With Kotlin]
 +
 +
==Scala==
 +
[https://deeplearning4j.org/scala Scala, Apache Spark and Deeplearning4j]
 +
*[https://github.com/deeplearning4j/ScalNet ScalNet]是受[[Keras]]启发而为Deeplearning4j开发的[[Scala]]语言封装
 +
*[https://github.com/deeplearning4j/nd4s ND4S] Scala bindings for [[ND4J]]
 +
 +
==Clojure==
 +
[https://deeplearning4j.org/clojure Deep Learning With Clojure]
 +
 +
==[[C++]]==
 +
*[[JavaCPP]]
  
 
==图集==
 
==图集==
 
<gallery>
 
<gallery>
 
image:deeplearning4j-overview.png|DL4J
 
image:deeplearning4j-overview.png|DL4J
 +
image:dl4j-eco-cn.jpg|DL4J组件
 
image:deep-learning-use-case-industries.png|工业应用
 
image:deep-learning-use-case-industries.png|工业应用
 
image:deeplearning4j-ui.png|DL4J UI
 
image:deeplearning4j-ui.png|DL4J UI
 +
image:deeplearning4j-training-ui.png|训练UI
 
image:neural-network-table.png|神经网络
 
image:neural-network-table.png|神经网络
 
image:Deeplearning4j-Reference-Architecture-CPU-GPU-Training.png|DL4J参考架构:训练
 
image:Deeplearning4j-Reference-Architecture-CPU-GPU-Training.png|DL4J参考架构:训练
 
image:Deeplearning4j-Reference-Architecture-CPU-GPU-Scoring.png|DL4J参加架构:得分
 
image:Deeplearning4j-Reference-Architecture-CPU-GPU-Scoring.png|DL4J参加架构:得分
 +
image:SKIL-Reference-Architecture.png|SKIL参考架构
 
</gallery>
 
</gallery>
  
 
==链接==
 
==链接==
*[http://deeplearning4j.org/zh-index.html deeplearning4j官网]
+
*[https://deeplearning4j.org/ deeplearning4j官网]
*[https://github.com/deeplearning4j/deeplearning4j deeplearning4j @ github]
+
*[https://github.com/eclipse/deeplearning4j deeplearning4j @ github]
 
*[http://docs.huihoo.com/javadoc/deeplearning4j/ deeplearning4j javadoc]
 
*[http://docs.huihoo.com/javadoc/deeplearning4j/ deeplearning4j javadoc]
 
*[http://deeplearning4j.org/glossary 深度学习词汇表]
 
*[http://deeplearning4j.org/glossary 深度学习词汇表]
 
*[http://deeplearning4j.org/compare-dl4j-torch7-pylearn.html DL4J vs. Torch vs. Theano vs. Caffe vs. TensorFlow]
 
*[http://deeplearning4j.org/compare-dl4j-torch7-pylearn.html DL4J vs. Torch vs. Theano vs. Caffe vs. TensorFlow]
*[http://skymind.io/ Skymind]是DL4J的商业支持机构
+
*[https://skymind.ai Skymind]是DL4J的商业支持机构
  
 
[[category:deep learning]]
 
[[category:deep learning]]
第67行: 第101行:
 
[[category:scala]]
 
[[category:scala]]
 
[[category:clojure]]
 
[[category:clojure]]
 +
[[category:eclipse]]
 +
[[category:huihoo]]

2022年4月11日 (一) 02:09的最后版本

deeplearning4j(DL4j)

DL4J

目录

[编辑] 简介

Eclipse Deeplearning4j

deeplearning4j:开源(Apache v2)神经网络平台,基于 Apache Hadoop, Apache Spark 构建,为 Java, Scala & Clojure 编程语言提供的深度学习库。


[编辑] 新闻

  • 2017 年 10 月,Skymind 加入了 Eclipse 基金会,并且将 DL4J 贡献给开源 Java Enterprise Edition 生态系统。

[编辑] 指南

git clone https://github.com/eclipse/deeplearning4j-examples
cd deeplearning4j-examples
mvn clean install

使用 IntelliJ IDEA 打开项目,完成DL4J第一次体验

[编辑] 应用场景

神经网络应用情景

  • 人脸/图像识别
  • 语音搜索
  • 文本到语音(转录)
  • 垃圾邮件筛选(异常情况探测)
  • 欺诈探测
  • 推荐系统(客户关系管理、广告技术、避免用户流失)
  • 回归分析

[编辑] DL4J神经网络

如何选择神经网络

[编辑] 为何选择DL4J

为何选择Deeplearning4j?

[编辑] 推荐引擎

Build a Recommendation Engine With DL4J

[编辑] Spark

[编辑] Kotlin

Using Deeplearning4j With Kotlin

[编辑] Scala

Scala, Apache Spark and Deeplearning4j

[编辑] Clojure

Deep Learning With Clojure

[编辑] C++

[编辑] 图集

[编辑] 链接

分享您的观点
个人工具
名字空间

变换
操作
导航
工具箱