```
m = X.shape[1]
for i in range(self.nh+1):
self.W[i+1] -= learning_rate * dW[i+1] / m
self.B[i+1] -= learning_rate * dB[i+1] / m
```

This is part of the Feedfoward networks course. Sir mentions that you divide by the number of items. Does number of items mean number of features or number of training examples?