Python uses numpy to implement the BP neural network, numpybp

Python uses numpy to implement the BP neural network, numpybp

This article uses numpy to implement a simple BP neural network. Because it is used for regression rather than classification, the incentive function selected at the output layer is f (x) = x. The principle of BP neural network is not described here.

Import numpy as np class NeuralNetwork (object): def _ init _ (self, input_nodes, hidden_nodes, output_nodes, learning_rate): # Set number of nodes in input, hidden and output layers. set the number of nodes in the input, hidden, and output layers. input_nodes = input_nodes self. hidden_nodes = hidden_nodes self. output_nodes = output_nodes # Initialize weights, Initialize weight and learning rate self. weights_input_to_hidden = np. random. normal (0.0, self. hidden_nodes **-0.5, (self. hidden_nodes, self. input_nodes) self. weights_hidden_to_output = np. random. normal (0.0, self. output_nodes **-0.5, (self. output_nodes, self. hidden_nodes) self. lr = learning_rate # the excitation function of the hidden layer is the sigmoid function, and the Activation function is the sigmoid function self. activation_function = (lambda x: 1/(1 + np. exp (-x) def train (self, inputs_list, targets_list): # Convert inputs list to 2d array inputs = np. array (inputs_list, ndmin = 2 ). T # the shape of the input vector is [feature_diemension, 1] targets = np. array (targets_list, ndmin = 2 ). T # Forward propagation, Forward pass # TODO: Hidden layer hidden_inputs = np. dot (self. weights_input_to_hidden, inputs) # signals into hidden layer hidden_outputs = self. activation_function (hidden_inputs) # signals from hidden layer # The excitation function of the output layer is y = x final_inputs = np. dot (self. weights_hidden_to_output, hidden_outputs) # signals into final output layer final_outputs = final_inputs # signals from final output layer ### Back Propagation Backward pass, use gradient descent to update the weight #### Output error # output layer error is the difference between desired target and actual Output. output_errors = (targets_list-final_outputs) # Backpropagation error Backpropagated error # errors propagated to the hidden layer hidden_errors = np. dot (output_errors, self. weights_hidden_to_output) * (hidden_outputs * (1-hidden_outputs )). T # Update weight update the weights # Update the weight between the hidden layer and the output layer update hidden-to-output weights with gradient descent step self. weights_hidden_to_output + = output_errors * hidden_outputs.T * self. lr # update the weight between the input layer and the hidden layer update input-to-hidden weights with gradient descent step self. weights_input_to_hidden + = (inputs * hidden_errors * self. lr ). T # prediction def run (self, inputs_list): # Run a forward pass through the network inputs = np. array (inputs_list, ndmin = 2 ). T #### Implement forward Propagation Implement the forward pass here #### Hidden layer hidden_inputs = np. dot (self. weights_input_to_hidden, inputs) # signals into hidden layer hidden_outputs = self. activation_function (hidden_inputs) # signals from hidden layer # Output layer final_inputs = np. dot (self. weights_hidden_to_output, hidden_outputs) # signals into final output layer final_outputs = final_inputs # signals from final output layer return final_outputs

The above is all the content of this article. I hope it will be helpful for your learning and support for helping customers.