Vectorization
From Ufldl
(removed question, see details in talk page) |
|||
Line 1: | Line 1: | ||
When working with learning algorithms, having a faster piece of code often | When working with learning algorithms, having a faster piece of code often | ||
- | means that you'll make progress faster on your | + | means that you'll make progress faster on your project. For example, if your |
learning algorithm takes 20 minutes to run to completion, that means you can | learning algorithm takes 20 minutes to run to completion, that means you can | ||
"try" up to 3 new ideas per hour. But if your code takes 20 hours to | "try" up to 3 new ideas per hour. But if your code takes 20 hours to | ||
- | run, that | + | run, that means you can "try" only one idea a day, since that's |
how long you have to wait to get feedback from your program. In this latter | how long you have to wait to get feedback from your program. In this latter | ||
case, if you can speed up your code so that it takes only 10 hours to run, | case, if you can speed up your code so that it takes only 10 hours to run, | ||
- | that can literally double your productivity | + | that can literally double your personal productivity! |
'''Vectorization''' refers to a powerful way to speed up your algorithms. | '''Vectorization''' refers to a powerful way to speed up your algorithms. |