简单的全连接神经网络python代码

Sure, here's a simple example of a fully connected neural network in Python:

import numpy as np 

# Define the sigmoid activation function 
def sigmoid(x): 
    return 1/(1+np.exp(-x)) 

# Define the derivative of the sigmoid function 
def sigmoid_derivative(x): 
    return x*(1-x) 

# Define the input dataset 
X = np.array([[0,0,1],[0,1,1],[1,0,1],[1,1,1]]) 

# Define the output dataset 
y = np.array([[0],[1],[1],[0]]) 

# Set the random seed 
np.random.seed(1) 

# Initialize the weights randomly with mean 0 
synaptic_weights = 2*np.random.random((3,1)) - 1 

# Train the neural network 
for i in range(20000): 

    # Forward propagation 
    layer0 = X 
    layer1 = sigmoid(np.dot(layer0,synaptic_weights)) 

    # Calculate the error 
    layer1_error = y - layer1 

    # Multiply the error by the slope of the sigmoid at the values in layer1 
    layer1_delta = layer1_error * sigmoid_derivative(layer1) 

    # Update the weights 
    synaptic_weights += np.dot(layer0.T,layer1_delta) 

# Print the final output 
print("Output after training:",layer1)

This neural network has one hidden layer with three neurons and uses the sigmoid activation function. The output is binary, with values of either 0 or 1. The network is trained on a small dataset (X) with corresponding labels (y) using stochastic gradient descent (SGD).