[ML] Neural Network 예제

import numpy 
# scipy.special for the sigmoid function expit()
import scipy.special

#neural network class definition 

class neuralNetwork: 

#initialise the neural network 

    def __init__(self, inputnodes, hiddennodes, outputnodes,  learningrate): 
        
#set number of nodes in each input, hidden, output layer  
          self.inodes = inputnodes
          self.hnodes = hiddennodes
          self.onodes = outputnodes


# link weight matrices, wih & who
# weights inside the arrays are w_i_j , where link is from node i to node j in the next layer

       #  self.wih = (numpy.random.rand(self.hnodes, self.inodes) - 0.5)
       #  self.who = (numpy.random.rand(self.onodes, self.hnodes) - 0.5)
          self.wih = numpy.random.normal(0.0, pow(self.inodes, -0.5), (self.hnodes, self.inodes))
          self.who = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.onodes, self.hnodes))
            
#learning rate
          self.lr = learning_rate 
       
# activation function is the sigmoid function
          self.activation_function = lambda x: scipy.special.expit(x)
    
#train the neural network
    def train(self, inputs_list, targets_list): 
        # convert inputs list into 2d arrays
        inputs = numpy.array(inputs_list, ndmin = 2).T  
        targets = numpy.array(targets_list, ndmin = 2).T  
        
        # calculate signals into hidden layer
        hidden_inputs = numpy.dot(self.wih, inputs)        
        # calculate the signals emerging from hidden layer
        hidden_outputs = self.activation_function(hidden_inputs)
        # calculate signals into final output layer
        final_inputs = numpy.dot(self.who, hidden_outputs)
        # calculate the signals emerging from final output layer
        final_outputs = self.activation_function(final_inputs)    
            
        # error is the (target - actual)
        output_errors = targets - final_outputs   
        # hidden layer error is the output_errors, split by weights, recombined at hidden nodes
        hidden_errors = numpy.dot(self.who.T, output_errors)   
        
        # update the weights for the links between the hidden & output layers
        self.who += self.lr * numpy.dot((output_errors*final_outputs*(1.0-final_outputs)), numpy.transpose(hidden_outputs))
        # update the weights for the links between the input & hidden layers
        self.wih += self.lr * numpy.dot((hidden_errors*hidden_outputs*(1.0-hidden_outputs)), numpy.transpose(inputs))   
        
        return final_outputs
        #return output_errors
    
# query the neural network
    def query(self, inputs_list):
        # convert inputs list into 2d arrays
        inputs = numpy.array(inputs_list, ndmin = 2).T
        
        # calculate signals into hidden layer
        hidden_inputs = numpy.dot(self.wih, inputs)
        
        
        # calculate the signals emerging from hidden layer
        hidden_outputs = self.activation_function(hidden_inputs)

        # calculate signals into final output layer
        final_inputs = numpy.dot(self.who, hidden_outputs)

        # calculate the signals emerging from final output layer
        final_outputs = self.activation_function(final_inputs)
        
        
        return final_outputs
    
#Main code
#number of input, hidden and output nodes  
input_nodes = 2 
hidden_nodes = 2
output_nodes = 2

#learning rate is 0.3  
learning_rate = 0.3
    
#create instance of neural network 
n = neuralNetwork(input_nodes,hidden_nodes,output_nodes, learning_rate) 
final_outputs = n.query([0.05,0.10])
print('*')
print(final_outputs)
for e in range(10):
    n.train([0.05,0.10],[0.01,0.99])
print('**')
outputs = n.query([0.05,0.10])
print(outputs)

for e in range(100):
    n.train([0.05,0.10],[0.01,0.99])
print('**')
outputs = n.query([0.05,0.10])
print(outputs)

for e in range(10000):
    n.train([0.05,0.10],[0.01,0.99])
print('**')
outputs = n.query([0.05,0.10])
print(outputs)

https://github.com/erica00j/machinelearning/blob/main/NN1.ipynb

GitHub - erica00j/machinelearning