Learn AI by building it, from a single dot product to a transformer.
Short reads, figures you can drag.
Six questions. Pass at 80%.
Your code, checked in the browser.
A guided build on real data.
def softmax(z): z = z - z.max(axis=1, keepdims=True) e = np.exp(z) return e / e.sum(axis=1, keepdims=True)
With your name on it.
See it full size →