文件名称:DeepLearning-master
介绍说明－－下载内容均来自于网络，请自行研究使用
深度学习的概念源于人工神经网络的研究。含多隐层的多层感知器就是一种深度学习结构。深度学习通过组合低层特征形成更加抽象的高层表示属性类别或特征，以发现数据的分布式特征表示。[1]
深度学习的概念由Hinton等人于2006年提出。基于深信度网(DBN)提出非监督贪心逐层训练算法，为解决深层结构相关的优化难题带来希望，随后提出多层自动编码器深层结构。此外Lecun等人提出的卷积神经网络是第一个真正多层结构学习算法，它利用空间相对关系减少参数数目以提高训练性能。[1]
深度学习是机器学习研究中的一个新的领域，其动机在于建立、模拟人脑进行分析学习的神经网络，它模仿人脑的机制来解释数据，例如图像，声音和文本。
同机器学习方法一样，深度机器学习方法也有监督学习与无监督学习之分．不同的学习框架下建立的学习模型很是不同．例如，卷积神经网络（Convolutional neural networks，简称CNNs）就是一种深度的监督学习下的机器学习模型，而深度置信网（Deep Belief Nets，简称DBNs）就是一种无监督学习下的机器学习模型。
-Research on the concept of deep learning the artificial neural network. Multi hidden layer of multi-layer perceptron is a deep learning structure. Deep learning features a more abstract representation of a higher level representation of a feature class or feature to find data. [1]
Deep learning s concept by Hinton et al. In 2006. Based on the (DBN), a non supervised greedy layer by layer training algorithm is proposed to solve the problems of the deep structure. In addition, the convolutional neural network proposed by Lecun et al is the first real multi layer structure learning algorithm, which uses the relative relationship between the number of parameters to improve the training performance. [1]
Deep learning is a new field in machine learning research. The motivation is to establish and simulate the human brain to analyze the learning of neural network, which simulates the human brain mechanism to explain the data, such as image, sound and text.
Convolutional (neural) net
(系统自动生成,下载前可以参看下载内容)
下载文件列表
DeepLearning-master
...................\.gitignore
...................\README.md
...................\c
...................\.\DBN.c
...................\.\DBN.h
...................\.\HiddenLayer.h
...................\.\LogisticRegression.c
...................\.\LogisticRegression.h
...................\.\RBM.c
...................\.\RBM.h
...................\.\SdA.c
...................\.\SdA.h
...................\.\dA.c
...................\.\dA.h
...................\.\utils.h
...................\cpp
...................\...\DBN.cpp
...................\...\DBN.h
...................\...\HiddenLayer.cpp
...................\...\HiddenLayer.h
...................\...\LogisticRegression.cpp
...................\...\LogisticRegression.h
...................\...\RBM.cpp
...................\...\RBM.h
...................\...\SdA.cpp
...................\...\SdA.h
...................\...\dA.cpp
...................\...\dA.h
...................\...\utils.cpp
...................\go
...................\..\DBN.go
...................\..\HiddenLayer
...................\..\...........\HiddenLayer.go
...................\..\LogisticRegression.go
...................\..\LogisticRegression
...................\..\..................\LogisticRegression.go
...................\..\RBM.go
...................\..\RBM
...................\..\...\RBM.go
...................\..\SdA.go
...................\..\dA.go
...................\..\dA
...................\..\..\dA.go
...................\..\utils
...................\..\.....\utils.go
...................\java
...................\....\.gitkeep
...................\....\src
...................\....\...\DeepLearning
...................\....\...\............\DBN.java
...................\....\...\............\HiddenLayer.java
...................\....\...\............\LogisticRegression.java
...................\....\...\............\RBM.java
...................\....\...\............\SdA.java
...................\....\...\............\dA.java
...................\....\...\............\utils.java
...................\python
...................\......\CDBN.py
...................\......\CRBM.py
...................\......\DBN.py
...................\......\Dropout.py
...................\......\HiddenLayer.py
...................\......\LogisticRegression.py
...................\......\MLP.py
...................\......\RBM.py
...................\......\SdA.py
...................\......\dA.py
...................\......\utils.py
...................\scala
...................\.....\DBN.scala
...................\.....\HiddenLayer.scala
...................\.....\LogisticRegression.scala
...................\.....\RBM.scala
...................\.....\SdA.scala
...................\.....\dA.scala