Tuning hyper parameters when developing AI solutions is essential since the same models might behave quite differently with different parameters set. AI Practitioners recognize multiple hyper parameter tuning approaches and are able to quickly determine best set of hyper parameters for particular models using AI toolbox. In this course, you'll learn advanced techniques for hyper parameter tuning for AI development. You'll examine how to recognize the hyper parameters in ML and DL models. You'll learn about multiple hyper parameter tuning approaches and when to use each approach. Finally, you'll have a chance to tune hyper parameters for a real AI project using multiple techniques.
describe the role and importance of hyper parameters in AI development
describe the process of hyper parameter tuning and list multiple approaches to the process
describe the role of hyper parameters in common machine learning models and approaches
describe the role of hyper parameters in deep learning neural network models
specify how to tune hyper parameters using a Grid Search approach
specify how to tune hyper parameters using a Random Search approach
specify how to tune hyper parameters using Bayesian method
specify how to tune hyper parameters based on gradient
specify how to utilize evolutionary hyper parameter tuning
name multiple libraries that allow for hyper parameter tuning and describe how to use these libraries
work with the Python Grid Search algorithm for hyper parameter tuning of a machine learning model to configure optimal parameters and recognize an increase in accuracy
work with the Python Random Search algorithm for hyper parameter tuning of a machine learning model to configure optimal parameters and describe the advantages of using the Random Search algorithm