zoukankan      html  css  js  c++  java
  • 《机器学习》学习笔记(二):神经网络

            在解决一些简单的分类问题时,线性回归与逻辑回归就足以应付,但面对更加复杂的问题时(例如对图片中车的类型进行识别),运用之前的线性模型可能就得不到理想的结果,而且由于更大的数据量,之前方法的计算量也会变得异常庞大。因此我们需要学习一个非线性系统:神经网络。

            我在学习时,主要通过Andrew Ng教授提供的网络,而且文中多处都有借鉴Andrew Ng教授在mooc提供的资料。

            转载请注明出处:http://blog.csdn.net/u010278305

            神经网络在解决一些复杂的非线性分类问题时,相对于线性回归、逻辑回归,都被证明是一个更好的算法。其实神经网络也可以看做的逻辑回归的组合(叠加,级联等)。

            一个典型神经网络的模型如下图所示:

                                                               

            上述模型由3个部分组成:输入层、隐藏层、输出层。其中输入层输入特征值,输出层的输出作为我们分类的依据。例如一个20*20大小的手写数字图片的识别举例,那么输入层的输入便可以是20*20=400个像素点的像素值,即模型中的a1;输出层的输出便可以看做是该幅图片是0到9其中某个数字的概率。而隐藏层、输出层中的每个节点其实都可以看做是逻辑回归得到的。逻辑回归的模型可以看做这样(如下图所示):

                                                                                   

            有了神经网络的模型,我们的目的就是求解模型里边的参数theta,为此我们还需知道该模型的代价函数以及每一个节点的“梯度值”。

            代价函数的定义如下:

                                                                                          

          代价函数关于每一个节点处theta的梯度可以用反向传播算法计算出来。反向传播算法的思想是由于我们无法直观的得到隐藏层的输出,但我们已知输出层的输出,通过反向传播,倒退其参数。

    我们以以下模型举例,来说明反向传播的思路、过程:

                                                                                              

    该模型与给出的第一个模型不同的是,它具有两个隐藏层。

            为了熟悉这个模型,我们需要先了解前向传播的过程,对于此模型,前向传播的过程如下:

                                                                                       

    其中,a1,z2等参数的意义可以参照本文给出的第一个神经网络模型,类比得出。

    然后我们定义误差delta符号具有如下含义(之后推导梯度要用):

                                                         

    误差delta的计算过程如下:

                                                                             

    然后我们通过反向传播算法求得节点的梯度,反向传播算法的过程如下:

                                                  

    有了代价函数与梯度函数,我们可以先用数值的方法检测我们的梯度结果。之后我们就可以像之前那样调用matlab的fminunc函数求得最优的theta参数。

    需要注意的是,在初始化theta参数时,需要赋予theta随机值,而不能是固定为0或是什么,这就避免了训练之后,每个节点的参数都是一样的。

    下面给出计算代价与梯度的代码:

    function [J grad] = nnCostFunction(nn_params, ...
                                       input_layer_size, ...
                                       hidden_layer_size, ...
                                       num_labels, ...
                                       X, y, lambda)
    %NNCOSTFUNCTION Implements the neural network cost function for a two layer
    %neural network which performs classification
    %   [J grad] = NNCOSTFUNCTON(nn_params, hidden_layer_size, num_labels, ...
    %   X, y, lambda) computes the cost and gradient of the neural network. The
    %   parameters for the neural network are "unrolled" into the vector
    %   nn_params and need to be converted back into the weight matrices. 
    % 
    %   The returned parameter grad should be a "unrolled" vector of the
    %   partial derivatives of the neural network.
    %
    
    % Reshape nn_params back into the parameters Theta1 and Theta2, the weight matrices
    % for our 2 layer neural network
    Theta1 = reshape(nn_params(1:hidden_layer_size * (input_layer_size + 1)), ...
                     hidden_layer_size, (input_layer_size + 1));
    
    Theta2 = reshape(nn_params((1 + (hidden_layer_size * (input_layer_size + 1))):end), ...
                     num_labels, (hidden_layer_size + 1));
    
    % Setup some useful variables
    m = size(X, 1);
             
    % You need to return the following variables correctly 
    J = 0;
    Theta1_grad = zeros(size(Theta1));
    Theta2_grad = zeros(size(Theta2));
    
    % ====================== YOUR CODE HERE ======================
    % Instructions: You should complete the code by working through the
    %               following parts.
    %
    % Part 1: Feedforward the neural network and return the cost in the
    %         variable J. After implementing Part 1, you can verify that your
    %         cost function computation is correct by verifying the cost
    %         computed in ex4.m
    %
    % Part 2: Implement the backpropagation algorithm to compute the gradients
    %         Theta1_grad and Theta2_grad. You should return the partial derivatives of
    %         the cost function with respect to Theta1 and Theta2 in Theta1_grad and
    %         Theta2_grad, respectively. After implementing Part 2, you can check
    %         that your implementation is correct by running checkNNGradients
    %
    %         Note: The vector y passed into the function is a vector of labels
    %               containing values from 1..K. You need to map this vector into a 
    %               binary vector of 1's and 0's to be used with the neural network
    %               cost function.
    %
    %         Hint: We recommend implementing backpropagation using a for-loop
    %               over the training examples if you are implementing it for the 
    %               first time.
    %
    % Part 3: Implement regularization with the cost function and gradients.
    %
    %         Hint: You can implement this around the code for
    %               backpropagation. That is, you can compute the gradients for
    %               the regularization separately and then add them to Theta1_grad
    %               and Theta2_grad from Part 2.
    %
    J_tmp=zeros(m,1);
    for i=1:m
        y_vec=zeros(num_labels,1);
        y_vec(y(i))=1;
        a1 = [ones(1, 1) X(i,:)]';
        z2=Theta1*a1;
        a2=sigmoid(z2);
        a2=[ones(1,size(a2,2)); a2];
        z3=Theta2*a2;
        a3=sigmoid(z3);
        hThetaX=a3;
        J_tmp(i)=sum(-y_vec.*log(hThetaX)-(1-y_vec).*log(1-hThetaX));
    end
    J=1/m*sum(J_tmp);
    J=J+lambda/(2*m)*(sum(sum(Theta1(:,2:end).^2))+sum(sum(Theta2(:,2:end).^2)));
    
    Delta1 = zeros( hidden_layer_size, (input_layer_size + 1));
    Delta2 = zeros( num_labels, (hidden_layer_size + 1));
    for t=1:m
        y_vec=zeros(num_labels,1);
        y_vec(y(t))=1;
        a1 = [1 X(t,:)]';
        z2=Theta1*a1;
        a2=sigmoid(z2);
        a2=[ones(1,size(a2,2)); a2];
        z3=Theta2*a2;
        a3=sigmoid(z3);
        delta_3=a3-y_vec;
        gz2=[0;sigmoidGradient(z2)];
        delta_2=Theta2'*delta_3.*gz2;
        delta_2=delta_2(2:end);
        Delta2=Delta2+delta_3*a2';
        Delta1=Delta1+delta_2*a1';
    end
    Theta1_grad=1/m*Delta1;
    Theta2_grad=1/m*Delta2;
    
    Theta1(:,1)=0;
    Theta1_grad=Theta1_grad+lambda/m*Theta1;
    Theta2(:,1)=0;
    Theta2_grad=Theta2_grad+lambda/m*Theta2;
    % -------------------------------------------------------------
    
    % =========================================================================
    
    % Unroll gradients
    grad = [Theta1_grad(:) ; Theta2_grad(:)];
    
    
    end
    

    最后总结一下,对于一个典型的神经网络,训练过程如下:

                                        

                                       

    按照这个步骤,我们就可以求得神经网络的参数theta。

    转载请注明出处:http://blog.csdn.net/u010278305

  • 相关阅读:
    0425正则数组
    0424php函数
    0424php基础
    string类例题
    数组分为一维数组,二维数组,多为数组
    string类 截取的长度 是否包含某个数
    循环语句2
    /异常语句try,catch.
    string类
    循环语句
  • 原文地址:https://www.cnblogs.com/chenyn2014/p/4319123.html
Copyright © 2011-2022 走看看