Coding in Forward Prop

In General implementation of forward propagation from Neural network implementation in python can anyone explain the coding part (i.e)defining the dense function

I believe this is covered in the lectures.
Do you have a specific question?

for j in range(units):             
    w = W[:,j]                     
    z = np.dot(w, a_in) + b[j]     
    a_out[j] = g(z)                
return(a_out)

in this code what is the meaning for the w assignment

‘w’ is a vector, it is a copy of one of the columns of the W matrix.
This lets you use the np.dot() function between two vectors to compute the activation.