Multi-Layer Perceptron not working

Question

I am trying to implement a multi-layer perceptron using simple numpy. But, I am running into a road-block. There's a fair chance that I am not implementing it correctly as in the past I have always used a library for this purpose. I would really appreciate some help in debugging the code. It is less than 100 lines of code and hopefully, should not take up too much time. Thanks!

The details of my perceptron are as follows:

1. Inputs = 2
2. Output = 1
3. Hidden Layer Count = 5
4. Loss = Squared-Error

The following is my code:

(I have commented in all the places that seemed necessary)

import numpy as np
import matplotlib.pyplot as plt

#Sampling 100 random values uniformly distributed b/w 0 and 5.
x=np.random.uniform(low=0, high=5, size=(100,))
y=np.multiply(x,x)
#Storing the random values and their squares in x and y
x=np.reshape(x,(-1,1))
y=np.reshape(y,(-1,1))
# plt.plot(x,y, 'ro')
# plt.show()

#Network Initialisation
hSize=5
inputSize=1
outputSize=1
Wxh=np.random.rand(hSize, inputSize+1)
Woh=np.random.rand(outputSize, hSize+1)


#+++++++++++++Back-propagation++++++++++++++
iterations=100
WohGrad=np.zeros(Woh.shape)
WxhGrad=np.zeros(Wxh.shape)
for i in range(0, iterations):
    #+++++++++++++Forward Pass++++++++++++++
    #Input Layer
    z1=x[i]
    a1=z1
    h1=np.append([1], a1)
    #Hidden Layer-1
    z2=np.dot(Wxh, h1)
    a2=1/(1+np.exp(-z2))
    h2=np.append([1], a2)
    #Output Layer
    z3=np.dot(Woh, h2)
    a3=z3


    #+++++++++++++Backward Pass++++++++++++++
    #Squared Error
    pred=a3
    expected=y[i]
    loss=np.square(pred-expected)/2

    #Delta Values
    delta_3=(pred-expected)
    delta_2=np.multiply(np.dot(np.transpose(Woh), delta_3)[1:], 1/(1+np.exp(-z2) ))

    #Parameter Gradients and Update
    WohGrad=WohGrad+np.dot(delta_3,(h2.reshape(1,-1)))
    WxhGrad=WxhGrad+np.dot(delta_2.reshape(hSize,-1),(h1.reshape(1,-1)))

#Parameter Update
learningRate=0.01
L2_regularizer=0.01
WohGrad=WohGrad/iterations+L2_regularizer*Woh
WxhGrad=WxhGrad/iterations+L2_regularizer*Wxh
Wxh=Wxh-learningRate*WxhGrad
Woh=Woh-learningRate*WohGrad


#++++++++Testing++++++++++
#Forward Pass
#Input Layer
z1=np.array([2.5])
a1=z1
h1=np.append([1], a1)


#Hidden Layer-1
z2=np.dot(Wxh, h1)
a2=1/(1+np.exp(-z2))
h2=np.append([1], a2)
#Output Layer
z3=np.dot(Woh, h2)
a3=z3
print(a3)