Keras中建立神经网络测试XOR问题

来源：互联网发布：毕福剑酒桌上网络视频编辑：程序博客网时间：2024/05/16 13:18

#机器学习的课程中，XOR问题是必讲的一个例题，它能很好地帮助理解神经网络的工作过程。可是它只有4个样本，每个样本二维输入一维输出，太简单。实现来讲，体现不出#神经网络的强大来。# -*- coding: utf-8 -*-"""Created on Fri May 20 10:08:00 2016@author: Michelle"""from keras.models import Sequential    from keras.layers.core import Dense, Activation  from keras.optimizers import SGDimport numpy as np #input datax_train =  np.array([[0, 0], [0, 1], [1, 0], [1, 1]])y_label = np.array([0,1,1,0])#create models, with 1hidden layers    model = Sequential()    model.add(Dense(32, init='uniform', input_dim=2))    model.add(Activation('relu')) model.add(Dense(1))    model.add(Activation('sigmoid'))#trainingsgd = SGD(lr=0.05, decay=1e-6, momentum=0.9, nesterov=True)model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=["accuracy"])   hist = model.fit(x_train, y_label, batch_size=1, nb_epoch=100, shuffle=True, verbose=0,validation_split=0.0)print(hist.history)#evaluating model performanceloss_metrics = model.evaluate(x_train, y_label, batch_size=1)

0 0