Created
July 10, 2018 19:13
-
-
Save Thanatoz-1/9ca0f9eb36f01dfdb4351219fe97ae5c to your computer and use it in GitHub Desktop.
Deep learning fundamentals : Hyperparameters
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
Hyperparameter are simply 'knobs' and 'turns' used to tune the statistical model of deep learing. | |
They are model-specific properties that you fix even before specifying a network and further tune them to create the required fitting of your data. | |
List of few hyperparameters are: | |
1. Learning rate | |
2. Decay rate | |
3. Number of hidden layers | |
4. Dropout | |
5. Activation function | |
6. Momentum | |
7. Batch size & a lot other.. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment