Learn make your own neural network record (ii)

Through the previous theoretical study, as well as the analysis of the relationship between error and weight, derive the formula to practice doing a own neural network through Python3.5:

Follow the python introduction in the book and introduce the Zeros () in the NumPy:

Import= Numpy.zeros ([3,2= 1a[] = 2a[2,1] = 5print(a)

The result is:

[1.0.]
[0.2.]
[0.5.]

You can use this method to generate a matrix.

Next, use Python to build the skeleton of the neural network:

Build a basic model:

ImportNumPyclassneuralnetwork:def __init__(self, inputnodes, hiddennodes, Outputnodes, learningrate): Self.inodes=inputnodes self.hnodes=hiddennodes self.onodes=outputnodes SELF.LR=learningrate#generate the link weights between the range of-1 to +1Self.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))Pass    defTrain (self):Pass    defquery (self):Pass#TestInput_nodes = 3Hidden_nodes= 3Output_nodes= 3learning_rate= 0.5#Create instance of neural networkn = neuralnetwork (Input_nodes, Hidden_nodes, Output_nodes, Learning_rate)

The Cunstructor has a start node, a hidden node, and an output node, including learning rate.

Each link weight uses the form of a numpy random number to initialize a series of weight and then training data to find the error and reverse modify

Learn make your own neural network record (ii)