0
$\begingroup$

I have implemented a deep learning model using Keras library. A lot of data scientists said use Keras tuner to increase model performance. I am bit confuse

  1. what is Keras tuner and when should I use that?

  2. What is hyperparameter in Keras?

$\endgroup$
0
$\begingroup$

Hyperparameters are all the training variables set manually with a predetermined value before starting the training. You can think of Hyperparameters as configuration variables you set when running some software. We want to find the best configuration of hyperparameters which will give us the best score on the metric we care about on the validation / test set.

Keras Tuner helps mostly in hyperparameter tuning. Hyperparameter tuning refers to the process of searching for the best subset of hyperparameter values in some predefined space.

Keras Tuner comes inbuilt with many algorithm that help in hyperparameter tuning like Hyperband, and Random Search. So, it's provide us a easy way to do hyperparameter optimization.

Refer Keras Tuner Documentation to know more.

| improve this answer | |
$\endgroup$
0
$\begingroup$

Hyper-parameter refers to all the parameters that can be changed in a model. For example, the activation function is a hyper-parameter and you can put values such as relu or tanh. Another example is the optimizer. Even the number of neurons is a hyperparameter.

Keras Tuner helps in tuning the hyperparameters so as to get the best result.

| improve this answer | |
$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.