How to determine the size of biases? [closed]

I'm new to the world of machine learning. My question is how can I determine the size of the biases in a neural network (with backpropagation algorithm)? Currently, I have a 2-layer neural network (1 hidden and 1 output layer). Here's the code:

import numpy as np
from matplotlib import pyplot as plt

sigmoid = lambda x : 1 / (1 + np.exp(-x))
dsigmoid = lambda y: y * (1 - sigmoid(y))

# This function performs the given function (func) to the whole numpy array
def mapFunc(array, func) :
newArray = array.copy()
for element in np.nditer(newArray, op_flags=['readwrite']) :
element[...] = func(element)
return newArray

class NeuralNetwork :

def __init__(self, input_nodes, hidden_nodes, output_nodes) :
self.input_nodes = input_nodes
self.hidden_nodes = hidden_nodes
self.output_nodes = output_nodes

self.W_ih = np.random.rand(hidden_nodes, input_nodes)
self.W_ho = np.random.rand(output_nodes, hidden_nodes)

self.B_ih = np.random.rand(hidden_nodes, 1)
self.B_ho = np.random.rand(output_nodes, 1)

self.learningRate = 0.1

def predict(self, inputs) :
# Calculate hidden's output
H_output = np.dot(self.W_ih, inputs)
H_output += self.B_ih
H_output = mapFunc(H_output, sigmoid) # Activation

# Calculate output's output
O_output = np.dot(self.W_ho, H_output)
O_output += self.B_ho
O_output = mapFunc(O_output, sigmoid) # Activation

return O_output

def train(self, inputs, target) :
# Calculate hidden's output
H_output = np.dot(self.W_ih, inputs)
H_output += self.B_ih
H_output = mapFunc(H_output, sigmoid) # Activation

# Calculate output's output
O_output = np.dot(self.W_ho, H_output)
O_output += self.B_ho
O_output = mapFunc(O_output, sigmoid) # Activation

# Calculate output error :
O_error = O_output - target

# Calculate output delta
O_gradient = mapFunc(O_output, dsigmoid)

W_ho_delta = np.dot(O_gradient, np.transpose(H_output))

self.W_ho -= W_ho_delta

# Calculate hidden error :
W_ho_t = np.transpose(self.W_ho)
H_error = np.dot(W_ho_t, O_error)

# Calculate hidden delta :
H_gradient = mapFunc(H_output, dsigmoid)

W_ih_delta = np.dot(H_gradient, inputs)

self.W_ih -= W_ih_delta

return O_output

n = NeuralNetwork(2, 2, 1)

inputs = np.matrix([[1], [0], [1], [1], [0], [1], [0], [0]])

input_list = []
input_list.append([[1], [0]])
input_list.append([[0], [1]])
input_list.append([[1], [1]])
input_list.append([[0], [0]])

target = np.matrix([[0], [0], [1], [1]])

outputs = []
for i in range(50000) :
ind = np.random.randint(len(input_list))
inp = input_list[ind]
out = n.train(inp, target[ind]).tolist()
outputs.append(out[0][0])

print outputs
plt.plot(outputs)

plt.show()

newInput = [[1], [1]]
print (n.predict(newInput))


In the train function, the line self.B_ih += H_gradient throws me an error about their sizes not being equal. I even tried to make the biases only a single number but that didn't help as it gets changed by H_gradient to a matrix. So, is there something wrong in the bias itself or I did some other step(s) wrong?

The biases appear in the activation function and can be seen as node feature. Suppose you have act = sigmoid, X your input layer and W your first hidden layer weight matrix. Then the output matrix of this hidden layer will be act(X.dot(W)+b).