Function softmax

11_softmax_and_crossentropy.py:18–19

(x)

# -> squashes the output to be between 0 and 1 = probability
# sum of all probabilities is 1
def softmax(x):
    return np.exp(x) / np.sum(np.exp(x), axis=0)

x = np.array([2.0, 1.0, 0.1])
outputs = softmax(x)