数学之路(3)-机器学习(3)-机器学习算法-神经网络[16]

我们调用第三方的神经网络python组件继续进行更复杂的函数拟合，这次拟合一个比f(x)=sin(x)*0.6函数更复杂的函数f(x)=sin(x)*0.5+cos(x)*0.5

python代码如下

#!/usr/bin/env python#-*- coding: utf-8 -*-#bp ann 函数拟合sin*0.5+cos*0.5import neurolab as nlimport numpy as npimport matplotlib.pyplot as pltisdebug=False#x和d样本初始化train_x =[]d=[]samplescount=1000myrndsmp=np.random.rand(samplescount)for yb_i in xrange(0,samplescount):    train_x.append([myrndsmp[yb_i]*4*np.pi-2*np.pi])for yb_i in xrange(0,samplescount):    d.append(np.sin(train_x[yb_i])*0.5+np.cos(train_x[yb_i])*0.5)myinput=np.array(train_x)   mytarget=np.array(d)bpnet = nl.net.newff([[-2*np.pi, 2*np.pi]], [5, 1])err = bpnet.train(myinput, mytarget, epochs=800, show=100, goal=0.02)simd=[]for xn in xrange(0,len(train_x)):#        print "====================="#        print u"样本：%f=> "%(train_x[xn][0])        simd.append(bpnet.sim([train_x[xn]])[0][0])#        print simd[xn]#        print u"--正确目标值--"#        print d[xn]#        print "====================="        temp_x=[]temp_y=simdtemp_d=[]i=0for mysamp in train_x:     temp_x.append(mysamp[0])     temp_d.append(d[i][0])     i+=1                 x_max=max(temp_x)x_min=min(temp_x)y_max=max(max(temp_y),max(d))+0.2y_min=min(min(temp_y),min(d))-0.2    plt.xlabel(u"x")plt.xlim(x_min, x_max)plt.ylabel(u"y")plt.ylim(y_min, y_max)plt.title("http://blog.csdn.net/myhaspl" )lp_x1 = temp_xlp_x2 = temp_ylp_d = temp_dplt.plot(lp_x1, lp_x2, 'r*')plt.plot(lp_x1,lp_d,'b*')plt.show()

>>> runfile(r'I:\book_prog\ann_bpnhsincos1.py', wdir=r'I:\book_prog')
Epoch: 100; Error: 0.528978849953;
Epoch: 200; Error: 0.33336612138;
Epoch: 300; Error: 0.253337487331;
Epoch: 400; Error: 0.20472927421;
Epoch: 500; Error: 0.202153963051;
Epoch: 600; Error: 0.19900731385;
Epoch: 700; Error: 0.197426245762;
Epoch: 800; Error: 0.193607559472;
The maximum number of train epochs is reached
>>> 

拟合效果为：

本博客所有内容是原创，如果转载请注明来源

http://blog.csdn.net/u010255642