Search⌘ K
Home
Courses
Make Your Own Neural Network in Python

Python Code for a Basic Neural Network

Explore how to create and test a basic neural network in Python by writing a neural network class, importing necessary modules, and querying the network with example inputs to verify functionality.

We'll cover the following...

Neural network class

Let’s pause to check what the code for the neural network class we’re building up looks like. It should look something like this:

Python
# 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 and who
        # weights inside the arrays are w_i_j, where link is from node i to node j in the next layer
        # w11 w21
        # w12 w22 etc 
        self.wih = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.hnodes, self.inodes))
        self.who = numpy.random.normal(0.0, pow(self.onodes, -0.5), (self.onodes, self.hnodes))
        # learning rate
        self.lr = learningrate
        
        # activation function is the sigmoid function
        self.activation_function = lambda x: scipy.special.expit(x)
        
        pass
    
    # train the neural network
    def train():
        pass
    
    # query the neural network
    def query(self, inputs_list):
        # convert inputs list to 2d array
        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

That is just the class. Aside from that, we should be importing the numpy and scipy.special modules right at the top of the code in the cell.

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

Note that the query() function only needs the input_list. It doesn’t need any other input.

That’s good progress, and now we’ll look at the missing piece, the train() function. ...