|
What prevents exponential overflow when computing exp(x)? |
Answered by
Ultron09
Aug 28, 2026
Replies: 1 comment
|
Subtract max(x, axis=-1, keepdims=True) before applying np.exp to ensure exponents <= 0. |
0 replies
Answer selected by
Ultron09
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Subtract max(x, axis=-1, keepdims=True) before applying np.exp to ensure exponents <= 0.