Deep learning fundamentals : Hyperparameters

What are Hyper-Parameter?

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..