Hyperparameter tuning is a Machine Learning problem in which you need to choose optimal hyperparameters required for a learning algorithm. Its value is used to control the process of learning. It is not easy to understand the hyperparameters during the training process. This is the reason they are fixed before the training begins. They show important properties of the Machine Learning model such as its complexity or the speed of learning.
You can learn in-depth about Machine learning and hyperparameter tuning in this Machine Learning Course.
You should also, watch this tutorial to get a better understanding of Hyperparameter Tuning in Machine Learning: