What you'll do
In this tutorial, we will learn how to use Hypo module to optimize hyperparameters in TAZI AutoML platform.
Problem: Running machine learning models with initial algorithm settings usually does not yield most accurate results. In order to reach model's finest state, you need to optimize your hyperparameters.
Result: Possible increase on your machine learning model's success
What you'll learn
- How to optimize your hyperparameters easily
- Compare different set of hyperparameter values
- Apply your new acquired hyperparameters on a new model
If you want to request a demo, please contact us Request for Demo
Recommended Browsers
We recommend that you use the latest version of Chrome for the best experience.
After you login to the TAZI Deploy interface, you will be welcomed to the Solutions page. Solution means a use case that you want to solve.
Each Business Model that is generated is linked to a specific Solution (use case) in the system. When you click to any solution from the Solutions panel, you can see its own Business Models on the right side.
You can click on any Solution name from the Solutions panel and then you can navigate to Hypo Models from the left menu. In order to create a new Hypo Model you need to click + Hypo Model.
After you clicking + Hypo Model you need to configure your Business Model like you did TAZI AutoML Tutorial. After you done with Business Model configurations you will see Hypo Options section at the fourth step.
In Parameters to Optimize tab you can enter hyperparameters that you want to optimize with their candidate values. You can search a hyperparameter by typing in the pattern field. In the below example we add learning rate hyperparameter with the value 0.05. Once you enter the value you need to click plus button. When you done with values you can click Done button on the right bottom corner
After entering all your hyperparameters you can click Next in the bottom left corner.
You will see your hypo model that you just created. Now, you need start it from the Action menu.
Now, our hypo model started. Completion of the hypo model may take a while. You can see the process by clicking down arrow.
Once the runs finished, you can click Go to Hypo Model Details from the Action menu to compare results.
In this section, you will see how you can evaluate your hypo model performance.
After clicking on Hypo Model Details button, you will see a screen like below. On the top right section you can see which run has best result. In our example it is iteration:2 run:1 one as you can see.
At below part of the screen you see Hypo Iteration Results. In this section you can see detailed results for each run by expanding iterations and runs.
You can click Show Parameters button to see which hyperparameter set is responsible for this result. When you click Export Parameters button, it will download a txt file including hyperparameter values. Also, you can start a new run with these settings by clicking Create New Run button.