Sparse Autoencoder(一)
Neural Networks
We will use the following diagram to denote a single neuron:
This "neuron" is a computational unit that takes as input x1,x2,x3 (and a +1 intercept term), and outputs , where is called the activation function. In these notes, we will choose to be the sigmoid function:
Thus, our single neuron corresponds exactly to the input-output mapping defined by logistic regression.
Although these notes will use the sigmoid function, it is worth noting that another common choice for f is the hyperbolic tangent, or tanh, function:
Here are plots of the sigmoid and tanh functions:
Finally, one identity that'll be useful later: If f(z) = 1 / (1 + exp( − z)) is the sigmoid function, then its derivative is given by f'(z) = f(z)(1 − f(z))
sigmoid 函数 或 tanh 函数都可用来完成非线性映射
Neural Network model
A neural network is put together by hooking together many of our simple "neurons," so that the output of a neuron can be the input of another. For example, here is a small neural network:
In this figure, we have used circles to also denote the inputs to the network. The circles labeled "+1" are called bias units, and correspond to the intercept term. The leftmost layer of the network is called the input layer, and the rightmost layer the output layer (which, in this example, has only one node). The middle layer of nodes is called the hidden layer, because its values are not observed in the training set. We also say that our example neural network has 3 input units (not counting the bias unit), 3 hidden units, and 1 output unit.
Our neural network has parameters (W,b) = (W(1),b(1),W(2),b(2)), where we write to denote the parameter (or weight) associated with the connection between unit j in layer l, and unit i in layerl + 1. (Note the order of the indices.) Also, is the bias associated with unit i in layer l + 1.
We will write to denote the activation (meaning output value) of unit i in layer l. For l = 1, we also use to denote the i-th input. Given a fixed setting of the parameters W,b, our neural network defines a hypothesis hW,b(x) that outputs a real number. Specifically, the computation that this neural network represents is given by:
每层都是线性组合 + 非线性映射
In the sequel, we also let denote the total weighted sum of inputs to unit i in layer l, including the bias term (e.g., ), so that .
Note that this easily lends itself to a more compact notation. Specifically, if we extend the activation function to apply to vectors in an element-wise fashion (i.e., f([z1,z2,z3]) = [f(z1),f(z2),f(z3)]), then we can write the equations above more compactly as:
We call this step forward propagation.
Backpropagation Algorithm
for a single training example (x,y), we define the cost function with respect to that single example to be:
This is a (one-half) squared-error cost function. Given a training set of m examples, we then define the overall cost function to be:
J(W,b;x,y) is the squared error cost with respect to a single example; J(W,b) is the overall cost function, which includes the weight decay term.
Our goal is to minimize J(W,b) as a function of W and b. To train our neural network, we will initialize each parameter and each to a small random value near zero (say according to a Normal(0,ε2) distribution for some small ε, say 0.01), and then apply an optimization algorithm such as batch gradient descent.Finally, note that it is important to initialize the parameters randomly, rather than to all 0's. If all the parameters start off at identical values, then all the hidden layer units will end up learning the same function of the input (more formally, will be the same for all values of i, so that for any input x). The random initialization serves the purpose of symmetry breaking.
One iteration of gradient descent updates the parameters W,b as follows:
The two lines above differ slightly because weight decay is applied to W but not b.
The intuition behind the backpropagation algorithm is as follows. Given a training example (x,y), we will first run a "forward pass" to compute all the activations throughout the network, including the output value of the hypothesis hW,b(x). Then, for each node i in layer l, we would like to compute an "error term" that measures how much that node was "responsible" for any errors in our output.
For an output node, we can directly measure the difference between the network's activation and the true target value, and use that to define (where layer nl is the output layer). For hidden units, we will compute based on a weighted average of the error terms of the nodes that uses as an input. In detail, here is the backpropagation algorithm:
- 1,Perform a feedforward pass, computing the activations for layers L2, L3, and so on up to the output layer .
2,For each output unit i in layer nl (the output layer), set
For
For each node i in layer l, set
4,Compute the desired partial derivatives, which are given as:
We will use "" to denote the element-wise product operator (denoted ".*" in Matlab or Octave, and also called the Hadamard product), so that if , then . Similar to how we extended the definition of to apply element-wise to vectors, we also do the same for (so that ).
The algorithm can then be written:
- 1,Perform a feedforward pass, computing the activations for layers , , up to the output layer , using the equations defining the forward propagation steps
2,For the output layer (layer ), set
3,For
- Set
4,Compute the desired partial derivatives:
Implementation note: In steps 2 and 3 above, we need to compute for each value of . Assuming is the sigmoid activation function, we would already have stored away from the forward pass through the network. Thus, using the expression that we worked out earlier for , we can compute this as .
Finally, we are ready to describe the full gradient descent algorithm. In the pseudo-code below, is a matrix (of the same dimension as ), and is a vector (of the same dimension as ). Note that in this notation, "" is a matrix, and in particular it isn't " times ." We implement one iteration of batch gradient descent as follows:
- 1,Set , (matrix/vector of zeros) for all .
- 2,For to ,
- Use backpropagation to compute and .
- Set .
- Set .
- 3,Update the parameters:
Sparse Autoencoder(一)的更多相关文章
- Deep Learning 1_深度学习UFLDL教程:Sparse Autoencoder练习(斯坦福大学深度学习教程)
1前言 本人写技术博客的目的,其实是感觉好多东西,很长一段时间不动就会忘记了,为了加深学习记忆以及方便以后可能忘记后能很快回忆起自己曾经学过的东西. 首先,在网上找了一些资料,看见介绍说UFLDL很不 ...
- (六)6.5 Neurons Networks Implements of Sparse Autoencoder
一大波matlab代码正在靠近.- -! sparse autoencoder的一个实例练习,这个例子所要实现的内容大概如下:从给定的很多张自然图片中截取出大小为8*8的小patches图片共1000 ...
- UFLDL实验报告2:Sparse Autoencoder
Sparse Autoencoder稀疏自编码器实验报告 1.Sparse Autoencoder稀疏自编码器实验描述 自编码神经网络是一种无监督学习算法,它使用了反向传播算法,并让目标值等于输入值, ...
- 七、Sparse Autoencoder介绍
目前为止,我们已经讨论了神经网络在有监督学习中的应用.在有监督学习中,训练样本是有类别标签的.现在假设我们只有一个没有带类别标签的训练样本集合 ,其中 .自编码神经网络是一种无监督学习算法,它使用 ...
- CS229 6.5 Neurons Networks Implements of Sparse Autoencoder
sparse autoencoder的一个实例练习,这个例子所要实现的内容大概如下:从给定的很多张自然图片中截取出大小为8*8的小patches图片共10000张,现在需要用sparse autoen ...
- 【DeepLearning】Exercise:Sparse Autoencoder
Exercise:Sparse Autoencoder 习题的链接:Exercise:Sparse Autoencoder 注意点: 1.训练样本像素值需要归一化. 因为输出层的激活函数是logist ...
- Sparse AutoEncoder简介
1. AutoEncoder AutoEncoder是一种特殊的三层神经网络, 其输出等于输入:\(y^{(i)}=x^{(i)}\), 如下图所示: 亦即AutoEncoder想学到的函数为\(f_ ...
- Exercise:Sparse Autoencoder
斯坦福deep learning教程中的自稀疏编码器的练习,主要是参考了 http://www.cnblogs.com/tornadomeet/archive/2013/03/20/2970724 ...
- DL二(稀疏自编码器 Sparse Autoencoder)
稀疏自编码器 Sparse Autoencoder 一神经网络(Neural Networks) 1.1 基本术语 神经网络(neural networks) 激活函数(activation func ...
- sparse autoencoder
1.autoencoder autoencoder的目标是通过学习函数,获得其隐藏层作为学习到的新特征. 从L1到L2的过程成为解构,从L2到L3的过程称为重构. 每一层的输出使用sigmoid方法, ...
随机推荐
- 运维派 企业面试题2 创建10个 "十个随机字母_test.html" 文件
Linux运维必会的实战编程笔试题(19题) 企业面试题2: 使用for循环在/tmp/www目录下通过随机小写10个字母加固定字符串test批量创建10个html文件,名称例如为: --[root@ ...
- php数据类型及运算
数据类型: 标量类型: int(intege), float, string, bool 复合类型: array, object 特殊类型: null, resouce进制转换十进制转二进制decb ...
- 【J-meter】调试JDBC请求
参考资料: http://www.codesec.net/view/165234.html
- malloc()和free()的原理及实现
在C语言中只能通过malloc()和其派生的函数进行动态的申请内存,而实现的根本是通过系统调用实现的(在linux下是通过sbrk()系统调用实现). malloc()到底从哪里得到了内存空间?答案是 ...
- Mysql 锁表 for update (引擎/事务)
因为之前用过oracle,知道利用select * for update 可以锁表.所以很自然就想到在mysql中能不能适应for update来锁表呢. 学习参考如下 由于InnoDB预设是Row- ...
- HDU2452 Navy maneuvers 记忆化搜索
这题目意思能忍?读了半年,乱七八糟的 记忆化搜索 拖拖的,dp[i][0]代表以获得最小值为目标的船以i为起点.dp[i][1]代表以获得最大值为目标的船以i为起点.接下来暴力枚举入度为0的点为起点, ...
- [Poi] Build a Vue App with Poi
Poi uses the Vue babel presets by default, so there is no additional install required to get up-and- ...
- android 2048游戏实现
android 的2048小游戏完整实现:GridLayout布局(android 4.0及以上). 曾经做过一个2048的算法题,学了几天android,认为能够实现个安卓版的.也就动手写了个. 包 ...
- PipeCAD之管道标准库PipeStd(2)
PipeCAD之管道标准库PipeStd(2) eryar@163.com Key Words. PipeCAD, PipeStd, 管道设计软件,管件库 1. Introduction 管道标准部件 ...
- Linux LVM(逻辑卷管理)
Lvm基本应用 什么是LVM? LVM 的全称是 Logical Volume Manager.中文为逻辑卷管理.它是Linux对磁盘分区的一种管理机制.它在传统的硬盘(或硬盘分区)和文件系统之间建立 ...