Why does the cost in my implementation of a deep neural network increase after a few iterations? - numpy

Question

I am a beginner in machine learning and neural networks. Recently, after watching Andrew Ng's lectures on deep learning, I tried to implement a binary classifier using deep neural networks on my own.
However, the cost of the function is expected to decrease after each iteration.
In my program, it decreases slightly in the beginning, but rapidly increases later. I tried to make changes in learning rate and number of iterations, but to no avail. I am very confused.
Here is my code
1. Neural network classifier class
class NeuralNetwork:
def __init__(self, X, Y, dimensions, alpha=1.2, iter=3000):
self.X = X
self.Y = Y
self.dimensions = dimensions # Including input layer and output layer. Let example be dimensions=4
self.alpha = alpha # Learning rate
self.iter = iter # Number of iterations
self.length = len(self.dimensions)-1
self.params = {} # To store parameters W and b for each layer
self.cache = {} # To store cache Z and A for each layer
self.grads = {} # To store dA, dZ, dW, db
self.cost = 1 # Initial value does not matter
def initialize(self):
np.random.seed(3)
# If dimensions is 4, then layer 0 and 3 are input and output layers
# So we only need to initialize w1, w2 and w3
# There is no need of w0 for input layer
for l in range(1, len(self.dimensions)):
self.params['W'+str(l)] = np.random.randn(self.dimensions[l], self.dimensions[l-1])*0.01
self.params['b'+str(l)] = np.zeros((self.dimensions[l], 1))
def forward_propagation(self):
self.cache['A0'] = self.X
# For last layer, ie, the output layer 3, we need to activate using sigmoid
# For layer 1 and 2, we need to use relu
for l in range(1, len(self.dimensions)-1):
self.cache['Z'+str(l)] = np.dot(self.params['W'+str(l)], self.cache['A'+str(l-1)]) + self.params['b'+str(l)]
self.cache['A'+str(l)] = relu(self.cache['Z'+str(l)])
l = len(self.dimensions)-1
self.cache['Z'+str(l)] = np.dot(self.params['W'+str(l)], self.cache['A'+str(l-1)]) + self.params['b'+str(l)]
self.cache['A'+str(l)] = sigmoid(self.cache['Z'+str(l)])
def compute_cost(self):
m = self.Y.shape[1]
A = self.cache['A'+str(len(self.dimensions)-1)]
self.cost = -1/m*np.sum(np.multiply(self.Y, np.log(A)) + np.multiply(1-self.Y, np.log(1-A)))
self.cost = np.squeeze(self.cost)
def backward_propagation(self):
A = self.cache['A' + str(len(self.dimensions) - 1)]
m = self.X.shape[1]
self.grads['dA'+str(len(self.dimensions)-1)] = -(np.divide(self.Y, A) - np.divide(1-self.Y, 1-A))
# Sigmoid derivative for final layer
l = len(self.dimensions)-1
self.grads['dZ' + str(l)] = self.grads['dA' + str(l)] * sigmoid_prime(self.cache['Z' + str(l)])
self.grads['dW' + str(l)] = 1 / m * np.dot(self.grads['dZ' + str(l)], self.cache['A' + str(l - 1)].T)
self.grads['db' + str(l)] = 1 / m * np.sum(self.grads['dZ' + str(l)], axis=1, keepdims=True)
self.grads['dA' + str(l - 1)] = np.dot(self.params['W' + str(l)].T, self.grads['dZ' + str(l)])
# Relu derivative for previous layers
for l in range(len(self.dimensions)-2, 0, -1):
self.grads['dZ'+str(l)] = self.grads['dA'+str(l)] * relu_prime(self.cache['Z'+str(l)])
self.grads['dW'+str(l)] = 1/m*np.dot(self.grads['dZ'+str(l)], self.cache['A'+str(l-1)].T)
self.grads['db'+str(l)] = 1/m*np.sum(self.grads['dZ'+str(l)], axis=1, keepdims=True)
self.grads['dA'+str(l-1)] = np.dot(self.params['W'+str(l)].T, self.grads['dZ'+str(l)])
def update_parameters(self):
for l in range(1, len(self.dimensions)):
self.params['W'+str(l)] = self.params['W'+str(l)] - self.alpha*self.grads['dW'+str(l)]
self.params['b'+str(l)] = self.params['b'+str(l)] - self.alpha*self.grads['db'+str(l)]
def train(self):
np.random.seed(1)
self.initialize()
for i in range(self.iter):
#print(self.params)
self.forward_propagation()
self.compute_cost()
self.backward_propagation()
self.update_parameters()
if i % 100 == 0:
print('Cost after {} iterations is {}'.format(i, self.cost))
2. Testing code for odd or even number classifier
import numpy as np
from main import NeuralNetwork
X = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
Y = np.array([[1, 0, 1, 0, 1, 0, 1, 0, 1, 0]])
clf = NeuralNetwork(X, Y, [1, 1, 1], alpha=0.003, iter=7000)
clf.train()
3. Helper Code
import math
import numpy as np
def sigmoid_scalar(x):
return 1/(1+math.exp(-x))
def sigmoid_prime_scalar(x):
return sigmoid_scalar(x)*(1-sigmoid_scalar(x))
def relu_scalar(x):
if x > 0:
return x
else:
return 0
def relu_prime_scalar(x):
if x > 0:
return 1
else:
return 0
sigmoid = np.vectorize(sigmoid_scalar)
sigmoid_prime = np.vectorize(sigmoid_prime_scalar)
relu = np.vectorize(relu_scalar)
relu_prime = np.vectorize(relu_prime_scalar)
Output

Answer 1

I believe your cross-entropy derivative is wrong. Instead of this:
# WRONG!
self.grads['dA'+str(len(self.dimensions)-1)] = -(np.divide(self.Y, A) - np.divide(1-self.Y, A))
... do this:
# CORRECT
self.grads['dA'+str(len(self.dimensions)-1)] = np.divide(A - self.Y, (1 - A) * A)
See these lecture notes for the details. I think you meant the formula (5), but forgot 1-A. Anyway, use formula (6).