Created
August 27, 2017 14:10
-
-
Save victor-iyi/21fa5b4dc4ada191e76848a916ed0d9b to your computer and use it in GitHub Desktop.
Estimate how long to brute force 1000 possible weights to train a Neural network
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| time_taken_for_one_weight = 0.04 | |
| weights_to_try = 1000 | |
| weights_in_net = 8 # for 1 layer | |
| one_year = 3600*24*365 | |
| years_to_train = time_taken_for_one_weight*(weights_to_try**weights_in_net)/one_year | |
| print('{:,}'.format(years_to_train)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment