求python大神帮助!!急急急

lynn1111111

以下是single output neuron perceptron的source code... 想请大神们帮帮忙把它modify去two output neuron perceptron that candiscriminate training examples from four class labelstraining 的example如下：

Input features		Target outputs
Input 1	Input 2	Output 1	Output 2
1	1	-1	-1
1	2	-1	-1
2	-1	-1	1
2	0	-1	1
-1	2	1	-1
-2	1	1	-1
-1	-1	1	1
-2	-2	1	1

import numpy as np

class Perceptron(object):

    #learning_rate: float - Learning rate
    #weights:array - weight values
    #errors: list - number of wrong classification
    #epoch: int - max no of iteration (epoch)

    def __init__(self,learning_rate=0.01, epoch = 10):
        self.learning_rate = learning_rate
        self.epoch=epoch

    def training(self,X,y):
        #initilize the weight
        self.weights = np.random.rand(1+X.shape[1])
        self.errors = []
        no_of_samples = X.shape[0]

        for i in range(self.epoch):
            no_errors=0

            for j in range(no_of_samples):
                target = y[j]
                xj=X[j]
                predicted= self.predict(xj)
                diff = target - predicted # compute error
                update = self.learning_rate * diff #formula to update weight

                self.weights[1:]+=update * xj
                self.weights[0]+=update

                if(diff!=0.0):
                    no_errors+=1
            self.errors.append(no_errors)
            print("epoch # "+str(i)+"no of error ="+str(no_errors)+"\n")
        return self


    def predict(self,X):
        sum_of_input=self.net_input(X) #generate predicted output
        if(sum_of_input >= 0):
            return 1
        else:
            return -1

    def net_input(self,X):
        return np.dot(X,self.weights[1:])+self.weights[0] #np.dot is matrix multiplciation

    def model(self):
        print("Weight value of NN *the first is the bias.\n")

        for val in self.weights:
            print (str(val)+"\n")
####
#start to play
logicAnd = np.array([[1,1,1],
                   [1,0,-1],
                   [0,1,-1],
                   [0,0,-1]])

#start train
andgate= Perceptron(0.1,epoch=10)
X=np.array(logicAnd[:,0:2])
y=np.array(logicAnd[:,2])
andgate.training(X,y) # pass in input and target
andgate.model()

##test the NN
print(andgate.predict(np.array(X[0])))
print(andgate.predict(np.array(X[1])))
print(andgate.predict(np.array(X[2])))
print(andgate.predict(np.array(X[3])))

WilliamOng123

Input features
         
Target outputs
Input 1
Input 2
Output 1
Output 2
1
1
-1
-1
1
2
-1
-1
2
-1
-1
1
2
0
-1
1
-1
2
1
-1
-2
1
1
-1
-1
-1
1
1
-2
-2
1
1



import numpy as np

class Perceptron(object):

    #learning_rate: float - Learning rate
    #weights:array - weight values
    #errors: list - number of wrong classification
    #epoch: int - max no of iteration (epoch)

    def __init__(self,learning_rate=0.01, epoch = 10):
        self.learning_rate = learning_rate
        self.epoch=epoch

    def training(self,X,y):
        #initilize the weight
        self.weights = np.random.rand(1+X.shape[1])
        self.errors = []
        no_of_samples = X.shape[0]

        for i in range(self.epoch):
            no_errors=0

            for j in range(no_of_samples):
                target = y[j]
                xj=X[j]
                predicted= self.predict(xj)
                diff = target - predicted # compute error
                update = self.learning_rate * diff #formula to update weight

                self.weights[1:]+=update * xj
                self.weights[0]+=update

                if(diff!=0.0):
                    no_errors+=1
            self.errors.append(no_errors)
            print("epoch # "+str(i)+"no of error ="+str(no_errors)+"\n")
        return self


    def predict(self,X):
        sum_of_input=self.net_input(X) #generate predicted output
        if(sum_of_input >= 0):
            return 1
        else:
            return -1

    def net_input(self,X):
        return np.dot(X,self.weights[1:])+self.weights[0] #np.dot is matrix multiplciation

    def model(self):
        print("Weight value of NN *the first is the bias.\n")

        for val in self.weights:
            print (str(val)+"\n")
####
#start to play
logicAnd = np.array([[1,1,1],
                   [1,0,-1],
                   [0,1,-1],
                   [0,0,-1]])

#start train
andgate= Perceptron(0.1,epoch=10)
X=np.array(logicAnd[:,0:2])
y=np.array(logicAnd[:,2])
andgate.training(X,y) # pass in input and target
andgate.model()

##test the NN
print(andgate.predict(np.array(X[0])))
print(andgate.predict(np.array(X[1])))
print(andgate.predict(np.array(X[2])))
print(andgate.predict(np.array(X[3])))

candy-z

哈哈 有没有兴趣来新加坡it公司工作呀？感兴趣的话请发送简历到zouqing777@gmail.com