Why Dense Function Uses For Loop instead of Vector Operations

In the Week 1, Lab 3, Coffee Roasting Example; dense function uses a for loop to calculate activations as shown below:

def my_dense(a_in, W, b):
    units = W.shape[1]
    a_out = np.zeros(units)
    for j in range(units):               
        w = W[:,j]                                    
        z = np.dot(w, a_in) + b[j]         
        a_out[j] = g(z)               

However, I don’t understand why it does not use vector operations to calculate activations as below, which would be faster (if I am right):

# Define sigmoid function
def sigmoid(t):
    return 1 / (1 + np.exp(-t))

# Define deterministic function
def f(X, W, b):
    return X @ W + b

# Calculate first layer
a1 = sigmoid(f(X, W, b))

Note: Above code gives the same results.

Hi @edizferit ,

Please check the implementation instructions for Ex2. You will find that the instruction explained that for this exercise, a for loop is used, and vectorization is explored in later section. Please see below:

Exercise 2

Below, build a dense layer subroutine. The example in lecture utilized a for loop to visit each unit (j) in the layer and perform the dot product of the weights for that unit (W[:,j]) and sum the bias for the unit (b[j]) to form z. An activation function g(z) is then applied to that result. This section will not utilize some of the matrix operations described in the optional lectures. These will be explored in a later section.

1 Like

Thank you very much @Kic