我正在通过使用随机梯度下降的反向传播训练XOR神经网络.将神经网络的权重初始化为-0.5和0.5之间的随机值.神经网络在80%的时间内成功训练自己.然而有时它会在反向传播时"卡住".通过"卡住",我的意思是我开始看到纠错率下降.例如,在成功培训期间,总误差会随着网络的学习而迅速下降,如下所示:
...
...
Total error for this training set: 0.0010008071327708653
Total error for this training set: 0.001000750550254843
Total error for this training set: 0.001000693973929822
Total error for this training set: 0.0010006374037948094
Total error for this training set: 0.0010005808398488103
Total error for this training set: 0.0010005242820908169
Total error for this training set: 0.0010004677305198344
Total error for this training set: 0.0010004111851348654
Total error for this training set: 0.0010003546459349181
Total error for this training set: 0.0010002981129189812
Total error for this training set: 0.0010002415860860656 …