神经网络中的线性函数产生较大的输出值

我正在对iris数据集进行回归,以预测其类型。我使用相同的数据和相同的神经网络成功地进行了分类。对于分类,我使用tanh作为所有层中的激活函数。但对于回归,我在隐藏层使用tanh函数,在输出层使用单位函数。

import numpy as np

class BackPropagation:
    weight =[]
    output =[]
    layers =0
    eta = 0.1

    def __init__(self, x):
        self.layers = len(x)
        for i in range(self.layers-2):
        w = np.random.randn(x[i]+1,x[i+1]+1)
        self.weight.append(w)
        w = w = np.random.randn(x[-2]+1,x[-1])
        self.weight.append(w)

    def tanh(self,x):
        return np.tanh(x)

    def deriv_tanh(self,x):
        return 1.0-(x**2)

    def linear(self,x):
        return x

    def deriv_linear(self,x):
        return 1


    def training(self,in_data,target,epoch=100):
        bias = np.atleast_2d(np.ones(in_data.shape[0])*(-1)).T
        in_data = np.hstack((in_data,bias))
        print("Training Starts ......")

        while epoch!=0:
            epoch-=1
            self.output=[]
            self.output.append(in_data)
            # FORWARD PHASE
            for j in range(self.layers-2):
                y_in = np.dot(self.output[j],self.weight[j])
                y_out = self.tanh(y_in)
                self.output.append(y_out)

            y_in = np.dot(self.output[-1],self.weight[-1])
            y_out = self.linear(y_in)
            self.output.append(y_out)
            print("Weight Is")
            for i in self.weight:
                print(i)       

            # BACKWARD PHASE
            error = self.output[-1]-target
            print("ERROR IS")
            print(np.mean(0.5*error*error))
            delta=[]
            delta_o = error * self.deriv_linear(self.output[-1])
            delta.append(delta_o)

            for k in reversed(range(self.layers-2)):
                delta_h = np.dot(delta[-1],self.weight[k+1].T) * self.deriv_tanh(self.output[k+1])
                delta.append(delta_h)
            delta.reverse()

            # WEIGHT UPDATE

            for i in range(self.layers-1):
                self.weight[i] -= (self.eta * np.dot(self.output[i].T, delta[i]))

        print("Training complete !")
        print("ACCURACY IS")
        acc = (1.0-(0.5*error*error))*100
        print(np.mean(acc))

    def recall(self,in_data):
        in_data = np.atleast_2d(in_data)
        bias = np.atleast_2d(np.ones(in_data.shape[0])*(-1)).T
        in_data = np.hstack((in_data,bias))
        y_out = in_data.copy()
        for i in range(self.layers-2):
            y_in = np.dot(y_out,self.weight[i])
            y_out = self.tanh(y_in).copy()
        y_in = np.dot(y_out,self.weight[-1])
        y_out = self.linear(y_in).copy()
        return y_out
# MAIN
data = np.loadtxt("iris.txt",delimiter=",")
obj = BackPropagation([4,2,1])
in_data = data[:rows,:cols].copy()
target = data[:rows,cols:].copy()
obj.training(in_data,target)
print("ANSWER IS")
print(obj.recall(in_data))  

数据集是这样的。这里,前4列是特征,最后一列包含目标值。数据集中有150条这样的记录。

5.1,3.5,1.4,0.2,0
4.9,3.0,1.4,0.2,0
5.0,3.6,1.4,0.2,0
5.4,3.9,1.7,0.4,0
4.6,3.4,1.4,0.3,0
7.0,3.2,4.7,1.4,1
6.4,3.2,4.5,1.5,1
6.9,3.1,4.9,1.5,1
5.5,2.3,4.0,1.3,1
6.3,3.3,6.0,2.5,2
5.8,2.7,5.1,1.9,2
7.1,3.0,5.9,2.1,2
6.3,2.9,5.6,1.8,2

在每个历元之后,预测值都呈指数增长。并且,在50个时代内,代码将INF或-INF作为输出。我还尝试了不同的学习速率、隐藏层中的神经元数量、隐藏层数量、初始权重值、迭代次数等。 那么,如何使用误差反向传播的神经网络进行回归呢?